Paper Citation Record · LEDGER

Low-Resource Languages Jailbreak GPT-4

As of 22 August 2026, this Paper Citation Record lists 55 of 55 outbound references and 88 inbound Pith citation observations for arXiv:2310.02446.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2310.02446 v2

Coverage vector

measured 55 of 55 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-05-17T09:24:13.911401Z

measured 143 of 143 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-22T06:32:14.747728+00:00

measured 88 of 88 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-16T06:05:12.200545Z

measured 1 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: pith, observed 2026-08-05T02:28:24.338817Z

Reference resolution

55 of 55 outbound references displayed

verified exact35
verified fuzzy14
unresolved0
parse uncertain0
malformed identifier1
metadata mismatch5

External citation measurements

20
pith, observed 2026-08-05T02:28:24.338817Z

Outbound references

Observation 5e72d20d-cb82-4ea1-89b3-dc50d883d2a1 · outbound

This paper cites Jigsaw multilingual toxic comment classification.

Low-Resource Languages Jailbreak GPT-4 Jigsaw multilingual toxic comment classification

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T09:24:14.160455Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation e9a0fc17-468f-4c68-bd18-7f1c68c99cce · outbound

This paper cites Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback.

Low-Resource Languages Jailbreak GPT-4 Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback

Reference 2

Resolution: verified exact; local_arxiv, observed 2026-05-17T09:24:14.051786Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 0c7bde94-fae6-4b83-a86c-7ea8ff575dd3 · outbound

This paper cites Constitutional AI: Harmlessness from AI Feedback.

Low-Resource Languages Jailbreak GPT-4 Constitutional AI: Harmlessness from AI Feedback

Reference 3

Resolution: verified exact; local_arxiv, observed 2026-05-17T09:24:14.056610Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 6b329777-af2e-41bb-a5a0-df452fbdbe7b · outbound

This paper cites A Multitask, Multilingual, Multimodal Evaluation of ChatGPT on Reasoning, Hallucination, and Interactivity.

Low-Resource Languages Jailbreak GPT-4 A Multitask, Multilingual, Multimodal Evaluation of ChatGPT on Reasoning, Hallucination, and Interactivity

Reference 4

Resolution: verified exact; arxiv_id, observed 2026-05-17T19:58:48.184559Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation b5fb6dfc-815c-4b8a-ac26-79100018e9ff · outbound

This paper cites Building Machine Translation Systems for the Next Thousand Languages.

Low-Resource Languages Jailbreak GPT-4 Building Machine Translation Systems for the Next Thousand Languages

Reference 5

Resolution: verified exact; arxiv_id, observed 2026-05-17T09:24:14.067395Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 219cdd08-98ae-4c38-8b7d-cf470028a56c · outbound

This paper cites SeamlessM4T: Massively Multilingual & Multimodal Machine Translation.

Low-Resource Languages Jailbreak GPT-4 SeamlessM4T: Massively Multilingual & Multimodal Machine Translation

Reference 6

Resolution: metadata mismatch; arxiv_id, observed 2026-05-17T09:24:14.072280Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 13f29bdb-d3c3-4d2b-a314-aae22063b8a2 · outbound

This paper cites Systematic inequalities in language technology performance across the world’s languages.

Low-Resource Languages Jailbreak GPT-4 Systematic inequalities in language technology performance across the world’s languages

Reference 7

Resolution: verified exact; doi, observed 2026-05-17T09:24:13.988038Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation aaa59a1f-99e0-40dd-96fc-eb6c8f354cf4 · outbound

This paper cites Are aligned neural networks adversarially aligned?.

Low-Resource Languages Jailbreak GPT-4 Are aligned neural networks adversarially aligned?

Reference 8

Resolution: metadata mismatch; arxiv_id, observed 2026-05-17T09:24:14.078179Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation b01ba6a5-539a-49b6-ac68-ceef593ea4db · outbound

This paper cites Aim.

Low-Resource Languages Jailbreak GPT-4 Aim

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T09:24:14.195909Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 8b8efac4-acfa-4301-ba0d-53d29aa78aee · outbound

This paper cites Translatorbot.

Low-Resource Languages Jailbreak GPT-4 Translatorbot

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T09:24:14.156570Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation f591f313-3f61-4f47-a7e7-f7061bb8b0d7 · outbound

This paper cites How is chatgpt’ s behavior changing over time?.

Low-Resource Languages Jailbreak GPT-4 How is chatgpt’ s behavior changing over time?

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T09:24:14.152934Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 7a7bdd74-4784-4e57-8152-a089145dcfa0 · outbound

This paper cites CONAN - CO unter NA rratives through Nichesourcing: a Multilingual Dataset of Responses to Fight Online Hate Speech.

Low-Resource Languages Jailbreak GPT-4 CONAN - CO unter NA rratives through Nichesourcing: a Multilingual Dataset of Responses to Fight Online Hate Speech

Reference 12

Resolution: verified exact; doi, observed 2026-05-17T09:24:13.977286Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 18cc0caf-5821-472c-80b6-9923e21a9ac2 · outbound

This paper cites Language support.

Low-Resource Languages Jailbreak GPT-4 Language support

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T09:24:14.202322Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation e62dc9e1-ae2c-4462-b764-cd3397c9b422 · outbound

This paper cites No Language Left Behind: Scaling Human-Centered Machine Translation.

Low-Resource Languages Jailbreak GPT-4 No Language Left Behind: Scaling Human-Centered Machine Translation

Reference 14

Resolution: verified exact; local_arxiv, observed 2026-05-17T09:24:14.083503Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 04d3ddc6-f5a7-4f7b-bdf8-64de9578d4e5 · outbound

This paper cites Multilingual Jailbreak Challenges in Large Language Models.

Low-Resource Languages Jailbreak GPT-4 Multilingual Jailbreak Challenges in Large Language Models

Reference 15

Resolution: verified exact; arxiv_id, observed 2026-05-17T09:24:14.088763Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation d61f5fa9-4e48-4a36-bd26-410023f9f859 · outbound

This paper cites Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned.

Low-Resource Languages Jailbreak GPT-4 Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned

Reference 16

Resolution: verified exact; local_arxiv, observed 2026-05-17T09:24:14.093690Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation ca8d4468-837a-4cf2-9522-c86a72686373 · outbound

This paper cites The Capacity for Moral Self-Correction in Large Language Models.

Low-Resource Languages Jailbreak GPT-4 The Capacity for Moral Self-Correction in Large Language Models

Reference 17

Resolution: verified exact; arxiv_id, observed 2026-05-17T09:24:13.993100Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 2b9bd19b-c2ff-43e8-bece-f59a28d16c28 · outbound

This paper cites RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Models.

Low-Resource Languages Jailbreak GPT-4 RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Models

Reference 18

Resolution: verified exact; local_arxiv, observed 2026-05-17T09:24:14.001152Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation e7b74f7a-3319-40b6-9828-ee47aa8e1a69 · outbound

This paper cites ChatGPT Perpetuates Gender Bias in Machine Translation and Ignores Non-Gendered Pronouns: Findings across Bengali and Five other Low-Resource Languages.

Low-Resource Languages Jailbreak GPT-4 ChatGPT Perpetuates Gender Bias in Machine Translation and Ignores Non-Gendered Pronouns: Findings across Bengali and Five other Low-Resource Languages

Reference 19

Resolution: verified exact; arxiv_id, observed 2026-05-17T09:24:14.006742Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 0e89f9f4-fe39-4c91-8a25-cee6e716fd93 · outbound

This paper cites How Good Are GPT Models at Machine Translation? A Comprehensive Evaluation.

Low-Resource Languages Jailbreak GPT-4 How Good Are GPT Models at Machine Translation? A Comprehensive Evaluation

Reference 20

Resolution: metadata mismatch; arxiv_id, observed 2026-05-17T09:24:14.011839Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 0c0b38fe-4593-4552-94dd-9939bdb963cb · outbound

This paper cites CBBQ: A Chinese Bias Benchmark Dataset Curated with Human-AI Collaboration for Large Language Models.

Low-Resource Languages Jailbreak GPT-4 CBBQ: A Chinese Bias Benchmark Dataset Curated with Human-AI Collaboration for Large Language Models

Reference 21

Resolution: verified exact; arxiv_id, observed 2026-05-17T09:24:14.017094Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation cc8c84f2-b9fd-4b84-a239-02149dd89211 · outbound

This paper cites Adversarial Examples for Evaluating Reading Comprehension Systems.

Low-Resource Languages Jailbreak GPT-4 Adversarial Examples for Evaluating Reading Comprehension Systems

Reference 22

Resolution: verified exact; doi, observed 2026-05-17T09:24:13.958411Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 04bd32f9-f9f1-4d67-a811-b4c28128b5be · outbound

This paper cites Automatically auditing large language models via discrete optimization.

Low-Resource Languages Jailbreak GPT-4 Automatically auditing large language models via discrete optimization

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T09:24:14.188704Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 131b6eb3-5c38-44e4-a3ea-c702abe7d8a6 · outbound

This paper cites In: Zong, C., Xia, F., Li, W., Navigli, R.

Low-Resource Languages Jailbreak GPT-4 In: Zong, C., Xia, F., Li, W., Navigli, R

Reference 24

Resolution: malformed identifier; doi_truncated, observed 2026-05-17T09:24:13.966278Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 598b2da4-21a7-49c8-a406-61cd6a4a7fe3 · outbound

This paper cites ChatGPT Beyond English: Towards a Comprehensive Evaluation of Large Language Models in Multilingual Learning.

Low-Resource Languages Jailbreak GPT-4 ChatGPT Beyond English: Towards a Comprehensive Evaluation of Large Language Models in Multilingual Learning

Reference 25

Resolution: verified exact; arxiv_id, observed 2026-05-17T09:24:14.021973Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation a9e0449a-d2cf-4d77-a059-af389bc5cba1 · outbound

This paper cites Open Sesame! Universal Black Box Jailbreaking of Large Language Models.

Low-Resource Languages Jailbreak GPT-4 Open Sesame! Universal Black Box Jailbreaking of Large Language Models

Reference 26

Resolution: verified exact; arxiv_id, observed 2026-05-17T09:24:14.027167Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation a5b85d78-6265-42c0-9c07-e5efde7decc1 · outbound

This paper cites RAIN: Your Language Models Can Align Themselves without Finetuning.

Low-Resource Languages Jailbreak GPT-4 RAIN: Your Language Models Can Align Themselves without Finetuning

Reference 27

Resolution: verified exact; arxiv_id, observed 2026-05-17T09:24:14.031548Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 483431eb-9134-4d95-a57c-18e5efb866bd · outbound

This paper cites Jailbreaking ChatGPT via Prompt Engineering: An Empirical Study.

Low-Resource Languages Jailbreak GPT-4 Jailbreaking ChatGPT via Prompt Engineering: An Empirical Study

Reference 30

Resolution: verified exact; local_arxiv, observed 2026-05-17T09:24:14.036520Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 46f48306-cf34-4f9e-88dd-044c93055af9 · outbound

This paper cites Black box adversarial prompting for foundation models.

Low-Resource Languages Jailbreak GPT-4 Black box adversarial prompting for foundation models

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T09:24:14.184738Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 9d73e60d-b501-4dee-a32b-1e4db372e2c8 · outbound

This paper cites Mitigating harm in language models with conditional-likelihood filtration.

Low-Resource Languages Jailbreak GPT-4 Mitigating harm in language models with conditional-likelihood filtration

Reference 32

Resolution: verified exact; arxiv_id, observed 2026-05-17T09:24:14.042036Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation b99b48e9-72ed-4ed6-91a2-21029ab93649 · outbound

This paper cites Duolingo.

Low-Resource Languages Jailbreak GPT-4 Duolingo

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T09:24:14.164588Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 81e4e847-266b-464c-8427-c6cc4a671b6f · outbound

This paper cites GPT-4 Technical Report.

Low-Resource Languages Jailbreak GPT-4 GPT-4 Technical Report

Reference 34

Resolution: verified exact; local_arxiv, observed 2026-05-17T09:24:14.098278Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 8ad5a889-6ccd-40e0-a9b0-9d196c7f40ff · outbound

This paper cites Government of iceland.

Low-Resource Languages Jailbreak GPT-4 Government of iceland

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T09:24:14.172750Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 12a17a2d-2c7d-4e80-9324-431856a8b931 · outbound

This paper cites Training language models to follow instructions with human feedback.

Low-Resource Languages Jailbreak GPT-4 Training language models to follow instructions with human feedback

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T09:24:14.176969Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation ac28dea0-70dc-434f-8893-d5c0546ece81 · outbound

This paper cites Practical black-box attacks against machine learning.

Low-Resource Languages Jailbreak GPT-4 Practical black-box attacks against machine learning

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T09:24:14.180901Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 0787857b-a8df-42d5-bf61-374879735b70 · outbound

This paper cites Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing , year =.

Low-Resource Languages Jailbreak GPT-4 Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing , year =

Reference 38

Resolution: metadata mismatch; doi, observed 2026-05-17T09:24:13.984406Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 01370b94-dcf8-41bc-9c85-7ee731412362 · outbound

This paper cites Square one bias in NLP: Towards a multi-dimensional exploration of the research manifold.

Low-Resource Languages Jailbreak GPT-4 Square one bias in NLP: Towards a multi-dimensional exploration of the research manifold

Reference 39

Resolution: verified exact; doi, observed 2026-05-17T09:24:13.962385Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 60843afb-dff2-4f62-8c60-270121e8c023 · outbound

This paper cites Jais and Jais-chat: Arabic-Centric Foundation and Instruction-Tuned Open Generative Large Language Models.

Low-Resource Languages Jailbreak GPT-4 Jais and Jais-chat: Arabic-Centric Foundation and Instruction-Tuned Open Generative Large Language Models

Reference 40

Resolution: verified exact; arxiv_id, observed 2026-05-17T09:24:14.103926Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 7917c3f2-b8f1-4ea4-b9b0-9297702edb8b · outbound

This paper cites "Do Anything Now": Characterizing and Evaluating In-The-Wild Jailbreak Prompts on Large Language Models.

Low-Resource Languages Jailbreak GPT-4 "Do Anything Now": Characterizing and Evaluating In-The-Wild Jailbreak Prompts on Large Language Models

Reference 41

Resolution: verified exact; local_arxiv, observed 2026-05-17T09:24:14.108875Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 66951f9c-76a9-4887-ae4c-e98a35690c26 · outbound

This paper cites Why so toxic? measuring and triggering toxic behavior in open-domain chatbots.

Low-Resource Languages Jailbreak GPT-4 Why so toxic? measuring and triggering toxic behavior in open-domain chatbots

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T09:24:14.199218Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation acd2ece7-94dc-45ec-8189-b05f8640fc37 · outbound

This paper cites Universal Adversarial Attacks with Natural Triggers for Text Classification.

Low-Resource Languages Jailbreak GPT-4 Universal Adversarial Attacks with Natural Triggers for Text Classification

Reference 43

Resolution: verified exact; doi, observed 2026-05-17T09:24:13.980555Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 32623e82-77d5-40db-b16d-df78622b7075 · outbound

This paper cites Smith, and Luke Zettlemoyer.

Low-Resource Languages Jailbreak GPT-4 Smith, and Luke Zettlemoyer

Reference 44

Resolution: verified exact; doi, observed 2026-05-17T09:24:13.973601Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 627295d0-7e0d-414f-bf2a-5336c4321232 · outbound

This paper cites ChatGPT is not a good indigenous translator.

Low-Resource Languages Jailbreak GPT-4 ChatGPT is not a good indigenous translator

Reference 45

Resolution: verified exact; doi, observed 2026-05-17T09:24:13.969936Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 78c6ff0a-89ac-4663-8bcd-12509abdb6fc · outbound

This paper cites Llama 2: Open Foundation and Fine-Tuned Chat Models.

Low-Resource Languages Jailbreak GPT-4 Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 46

Resolution: verified exact; local_arxiv, observed 2026-05-17T09:24:14.113933Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 0ff6e151-ef5f-4007-ab47-ae345e7a2c26 · outbound

This paper cites Translated unleashes full gpt-4 potential for businesses operating in languages other than english.

Low-Resource Languages Jailbreak GPT-4 Translated unleashes full gpt-4 potential for businesses operating in languages other than english

Reference 47

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T09:24:14.168804Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 72278891-c65c-46c9-9701-4a09aece17b0 · outbound

This paper cites Universal adversarial triggers for attacking and analyzing NLP.

Low-Resource Languages Jailbreak GPT-4 Universal adversarial triggers for attacking and analyzing NLP

Reference 48

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T09:24:14.192562Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 8c99a8d6-11a8-41ac-a361-9c026a2860d2 · outbound

This paper cites doi: 10.18653/v1/D19-1221.

Low-Resource Languages Jailbreak GPT-4 doi: 10.18653/v1/D19-1221

Reference 49

Resolution: verified exact; doi, observed 2026-05-17T09:24:13.952968Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 0399a3eb-8607-4f73-8dc2-d8bbe1c13c06 · outbound

This paper cites All Languages Matter: On the Multilingual Safety of Large Language Models.

Low-Resource Languages Jailbreak GPT-4 All Languages Matter: On the Multilingual Safety of Large Language Models

Reference 50

Resolution: verified exact; arxiv_id, observed 2026-05-17T09:24:14.119258Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 49da06db-1474-4a09-96ad-1dec12bda0b5 · outbound

This paper cites Do-Not-Answer: A Dataset for Evaluating Safeguards in LLMs.

Low-Resource Languages Jailbreak GPT-4 Do-Not-Answer: A Dataset for Evaluating Safeguards in LLMs

Reference 51

Resolution: metadata mismatch; arxiv_id, observed 2026-05-17T09:24:14.124720Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 1ccc29c5-7f42-49ea-96e3-e2803bffaaea · outbound

This paper cites Jailbroken: How Does LLM Safety Training Fail?.

Low-Resource Languages Jailbreak GPT-4 Jailbroken: How Does LLM Safety Training Fail?

Reference 52

Resolution: verified exact; local_arxiv, observed 2026-05-17T09:24:14.129455Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 5a10364c-fc48-4275-aaf5-b3028be8ea66 · outbound

This paper cites Ethical and social risks of harm from Language Models.

Low-Resource Languages Jailbreak GPT-4 Ethical and social risks of harm from Language Models

Reference 53

Resolution: verified exact; local_arxiv, observed 2026-05-17T09:24:14.134418Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation f7fbf205-4ce9-41bc-af92-228ed6990f92 · outbound

This paper cites Prompting Multilingual Large Language Models to Generate Code-Mixed Texts: The Case of South East Asian Languages.

Low-Resource Languages Jailbreak GPT-4 Prompting Multilingual Large Language Models to Generate Code-Mixed Texts: The Case of South East Asian Languages

Reference 54

Resolution: verified exact; arxiv_id, observed 2026-05-17T09:24:14.139522Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation f61039f2-9233-45ab-8844-f48251c0a235 · outbound

This paper cites GPT-4 Is Too Smart To Be Safe: Stealthy Chat with LLMs via Cipher.

Low-Resource Languages Jailbreak GPT-4 GPT-4 Is Too Smart To Be Safe: Stealthy Chat with LLMs via Cipher

Reference 55

Resolution: verified exact; arxiv_id, observed 2026-05-17T09:24:14.144341Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 560fcd23-4622-413e-ae6f-a792a3e6af88 · outbound

This paper cites Red teaming ChatGPT via Jailbreaking: Bias, Robustness, Reliability and Toxicity.

Low-Resource Languages Jailbreak GPT-4 Red teaming ChatGPT via Jailbreaking: Bias, Robustness, Reliability and Toxicity

Reference 56

Resolution: verified exact; arxiv_id, observed 2026-05-17T09:24:14.149204Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 8bc99e31-5022-4f5d-8b1b-659d0ef8fd2e · outbound

This paper cites Universal and Transferable Adversarial Attacks on Aligned Language Models.

Low-Resource Languages Jailbreak GPT-4 Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 57

Resolution: verified exact; local_arxiv, observed 2026-05-17T09:24:14.046876Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Pith citing papers

Observation 5c98929d-04de-423b-b2d4-a0d746e7a400 · inbound

SmoothLLM: Defending Large Language Models Against Jailbreaking Attacks cites this paper.

SmoothLLM: Defending Large Language Models Against Jailbreaking Attacks Low-Resource Languages Jailbreak GPT-4

Reference 28

Resolution: verified exact; arxiv_id, observed 2026-05-17T09:24:14.203470Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation e8d8041c-31e1-4aaf-b901-14697704f486 · inbound

A StrongREJECT for Empty Jailbreaks cites this paper.

A StrongREJECT for Empty Jailbreaks Low-Resource Languages Jailbreak GPT-4

Reference 39

Resolution: verified exact; arxiv_id, observed 2026-05-17T09:24:14.203470Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation a0946d21-1906-4376-9f24-de60bb06111f · inbound

JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Models cites this paper.

JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Models Low-Resource Languages Jailbreak GPT-4

Reference 56

Resolution: verified exact; arxiv_id, observed 2026-05-17T09:24:14.203470Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation cb10f105-f8c0-45e0-9d87-63a9a4e5c86b · inbound

Jailbreak Attacks and Defenses Against Large Language Models: A Survey cites this paper.

Jailbreak Attacks and Defenses Against Large Language Models: A Survey Low-Resource Languages Jailbreak GPT-4

Reference 106

Resolution: verified exact; arxiv_id, observed 2026-05-17T09:24:14.203470Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 6db8d5bf-bcd9-4c2a-92b4-6db3aa4c1d04 · inbound

AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents cites this paper.

AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents Low-Resource Languages Jailbreak GPT-4

Reference 32

Resolution: verified exact; arxiv_id, observed 2026-05-17T09:24:14.203470Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 325a16ab-919d-4ae6-bb93-aa886cbbac89 · inbound

RV4Chatbot: Are Chatbots Allowed to Dream of Electric Sheep? cites this paper.

RV4Chatbot: Are Chatbots Allowed to Dream of Electric Sheep? Low-Resource Languages Jailbreak GPT-4

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-12T15:18:19.493168Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 05ad4eab-bcea-4e40-bfd1-acdf4810ba78 · inbound

Uhura: A Benchmark for Evaluating Scientific Question Answering and Truthfulness in Low-Resource African Languages cites this paper.

Uhura: A Benchmark for Evaluating Scientific Question Answering and Truthfulness in Low-Resource African Languages Low-Resource Languages Jailbreak GPT-4

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-12T04:53:50.564436Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 60f55bd8-5b5c-41fb-b07d-f676f96e7d5e · inbound

Aya Expanse: Combining Research Breakthroughs for a New Multilingual Frontier cites this paper.

Aya Expanse: Combining Research Breakthroughs for a New Multilingual Frontier Low-Resource Languages Jailbreak GPT-4

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-11T21:38:38.168765Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4a5f5dfe-42d3-458a-9933-33c402fa66f5 · inbound

JailPO: A Novel Black-box Jailbreak Framework via Preference Optimization against Aligned LLMs cites this paper.

JailPO: A Novel Black-box Jailbreak Framework via Preference Optimization against Aligned LLMs Low-Resource Languages Jailbreak GPT-4

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-11T11:17:49.105339Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3178df8e-113e-4b29-83db-0de3b2787764 · inbound

Large Language Model Safety: A Holistic Survey cites this paper.

Large Language Model Safety: A Holistic Survey Low-Resource Languages Jailbreak GPT-4

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-11T05:19:34.544425Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cea33b91-912b-4498-b599-90468491ec88 · inbound

CL-Attack: Textual Backdoor Attacks via Cross-Lingual Triggers cites this paper.

CL-Attack: Textual Backdoor Attacks via Cross-Lingual Triggers Low-Resource Languages Jailbreak GPT-4

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-11T01:03:12.321630Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a76bef2b-afc8-45d7-b375-199041cb38a0 · inbound

Safeguarding Large Language Models in Real-time with Tunable Safety-Performance Trade-offs cites this paper.

Safeguarding Large Language Models in Real-time with Tunable Safety-Performance Trade-offs Low-Resource Languages Jailbreak GPT-4

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-10T22:35:27.002467Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e088c2cf-5dc4-4985-8771-c216233db363 · inbound

Self-Instruct Few-Shot Jailbreaking: Decompose the Attack into Pattern and Behavior Learning cites this paper.

Self-Instruct Few-Shot Jailbreaking: Decompose the Attack into Pattern and Behavior Learning Low-Resource Languages Jailbreak GPT-4

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-10T20:35:52.877810Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b95ecf7d-e00e-4012-a4b9-cbdb8aefe43f · inbound

Text-Diffusion Red-Teaming of Large Language Models: Unveiling Harmful Behaviors with Proximity Constraints cites this paper.

Text-Diffusion Red-Teaming of Large Language Models: Unveiling Harmful Behaviors with Proximity Constraints Low-Resource Languages Jailbreak GPT-4

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-10T20:34:36.603073Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bc50e58e-37ee-492d-bc8c-52347c806179 · inbound

Model Tampering Attacks Enable More Rigorous Evaluations of LLM Capabilities cites this paper.

Model Tampering Attacks Enable More Rigorous Evaluations of LLM Capabilities Low-Resource Languages Jailbreak GPT-4

Reference 82

Resolution: unresolved; no resolver link, observed 2026-08-09T14:47:15.392539Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c6ca5c90-bcec-4041-8a42-ba1e7e58f2ab · inbound

KDA: A Knowledge-Distilled Attacker for Generating Diverse Prompts to Jailbreak LLMs cites this paper.

KDA: A Knowledge-Distilled Attacker for Generating Diverse Prompts to Jailbreak LLMs Low-Resource Languages Jailbreak GPT-4

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-09T04:22:00.605573Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0ef389d6-57e7-4057-a72b-6d2efaffec07 · inbound

Salamandra Technical Report cites this paper.

Salamandra Technical Report Low-Resource Languages Jailbreak GPT-4

Reference 213

Resolution: unresolved; no resolver link, observed 2026-08-08T04:58:34.959959Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f1577663-4b9b-47da-b1c0-c60ae7821c06 · inbound

Mind the Gap! Choice Independence in Using Multilingual LLMs for Persuasive Co-Writing Tasks in Different Languages cites this paper.

Mind the Gap! Choice Independence in Using Multilingual LLMs for Persuasive Co-Writing Tasks in Different Languages Low-Resource Languages Jailbreak GPT-4

Reference 139

Resolution: unresolved; no resolver link, observed 2026-08-07T21:10:57.781784Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ebe7a971-d1ae-4437-b7b3-138e698230a1 · inbound

The Hidden Dimensions of LLM Alignment: A Multi-Dimensional Analysis of Orthogonal Safety Directions cites this paper.

The Hidden Dimensions of LLM Alignment: A Multi-Dimensional Analysis of Orthogonal Safety Directions Low-Resource Languages Jailbreak GPT-4

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-07T23:08:02.401728Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 730a3e3a-2ccb-4d8d-a0d3-d2bd2b570796 · inbound

LLM-Safety Evaluations Lack Robustness cites this paper.

LLM-Safety Evaluations Lack Robustness Low-Resource Languages Jailbreak GPT-4

Reference 57

Resolution: verified exact; local_arxiv, observed 2026-05-23T01:27:21.257186Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 1478c16c-eb79-4363-b9f9-85aeea398296 · inbound

CipherBank: Exploring the Boundary of LLM Reasoning Capabilities through Cryptography Challenges cites this paper.

CipherBank: Exploring the Boundary of LLM Reasoning Capabilities through Cryptography Challenges Low-Resource Languages Jailbreak GPT-4

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-16T06:05:12.200545Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6e3891d3-7c1f-479f-962c-e7801b07c097 · inbound

JailbreaksOverTime: Detecting Jailbreak Attacks Under Distribution Shift cites this paper.

JailbreaksOverTime: Detecting Jailbreak Attacks Under Distribution Shift Low-Resource Languages Jailbreak GPT-4

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-16T05:57:58.376446Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9842d1c3-4b93-464b-aded-7334c802a1be · inbound

NeuRel-Attack: Neuron Relearning for Safety Disalignment in Large Language Models cites this paper.

NeuRel-Attack: Neuron Relearning for Safety Disalignment in Large Language Models Low-Resource Languages Jailbreak GPT-4

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-16T05:33:11.854124Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2d7480d4-067b-49c8-a9d8-bc8226d1286f · inbound

Unmasking the Canvas: A Dynamic Benchmark for Image Generation Jailbreaking and LLM Content Safety cites this paper.

Unmasking the Canvas: A Dynamic Benchmark for Image Generation Jailbreaking and LLM Content Safety Low-Resource Languages Jailbreak GPT-4

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-15T23:39:22.213472Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cc920407-b97d-4470-b445-96c8b683fbf3 · inbound

A Survey of Attacks on Large Language Models cites this paper.

A Survey of Attacks on Large Language Models Low-Resource Languages Jailbreak GPT-4

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-15T20:34:34.526897Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b9de7364-2f94-42ad-9a4c-27242dac9181 · inbound

Improving LLM Outputs Against Jailbreak Attacks with Expert Model Integration cites this paper.

Improving LLM Outputs Against Jailbreak Attacks with Expert Model Integration Low-Resource Languages Jailbreak GPT-4

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-15T20:36:57.255813Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 93bf1d20-5cec-4421-a34e-59cce3628d5e · inbound

Towards medical AI misalignment: a preliminary study cites this paper.

Towards medical AI misalignment: a preliminary study Low-Resource Languages Jailbreak GPT-4

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-07T14:52:16.928485Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 87021e4c-06e4-467e-89ff-3457213ba352 · inbound

Audio Jailbreak Attacks: Exposing Vulnerabilities in SpeechGPT in a White-Box Framework cites this paper.

Audio Jailbreak Attacks: Exposing Vulnerabilities in SpeechGPT in a White-Box Framework Low-Resource Languages Jailbreak GPT-4

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-07T14:27:06.090288Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cd2759c2-ef6a-4d2e-82df-7b5953be472a · inbound

Paths Not Taken: Understanding and Mending the Multilingual Factual Recall Pipeline cites this paper.

Paths Not Taken: Understanding and Mending the Multilingual Factual Recall Pipeline Low-Resource Languages Jailbreak GPT-4

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-07T13:58:20.347882Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3b49342b-9290-4a62-9060-ceded0969286 · inbound

Concealment of Intent: A Game-Theoretic Analysis cites this paper.

Concealment of Intent: A Game-Theoretic Analysis Low-Resource Languages Jailbreak GPT-4

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-07T13:53:40.616522Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9aaf56e4-1414-4bb6-8438-5260f479e868 · inbound

Expert Survey: AI Reliability & Security Research Priorities cites this paper.

Expert Survey: AI Reliability & Security Research Priorities Low-Resource Languages Jailbreak GPT-4

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-07T13:31:01.404747Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9a1dcd97-7d57-4a48-907f-8b3489064b64 · inbound

Compensating for Data with Reasoning: Low-Resource Machine Translation with LLMs cites this paper.

Compensating for Data with Reasoning: Low-Resource Machine Translation with LLMs Low-Resource Languages Jailbreak GPT-4

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-07T13:15:35.430375Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e7b22fde-4c56-45b1-8e2e-19c8d5f09556 · inbound

Prompt Attacks Reveal Superficial Knowledge Removal in Unlearning Methods cites this paper.

Prompt Attacks Reveal Superficial Knowledge Removal in Unlearning Methods Low-Resource Languages Jailbreak GPT-4

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-07T04:37:08.222926Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation feee3bb0-1f51-4cd0-a73d-c45e8e78c78d · inbound

Cross-Modal Obfuscation for Jailbreak Attacks on Large Vision-Language Models cites this paper.

Cross-Modal Obfuscation for Jailbreak Attacks on Large Vision-Language Models Low-Resource Languages Jailbreak GPT-4

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-06T23:42:42.798103Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cfe6234d-f633-4e9d-966c-6efa0979c478 · inbound

Bridging the Gap with Retrieval-Augmented Generation: Making Prosthetic Device User Manuals Available in Marginalised Languages cites this paper.

Bridging the Gap with Retrieval-Augmented Generation: Making Prosthetic Device User Manuals Available in Marginalised Languages Low-Resource Languages Jailbreak GPT-4

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-06T21:29:48.997312Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b3527ed0-15e6-4f3d-802b-ac57da5f1cef · inbound

`For Argument's Sake, Show Me How to Harm Myself!': Jailbreaking LLMs in Suicide and Self-Harm Contexts cites this paper.

`For Argument's Sake, Show Me How to Harm Myself!': Jailbreaking LLMs in Suicide and Self-Harm Contexts Low-Resource Languages Jailbreak GPT-4

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-06T21:05:19.158580Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6df9012a-c4cd-4d40-a6a2-5ea86222a8c9 · inbound

Beyond Weaponization: NLP Security for Medium and Lower-Resourced Languages in Their Own Right cites this paper.

Beyond Weaponization: NLP Security for Medium and Lower-Resourced Languages in Their Own Right Low-Resource Languages Jailbreak GPT-4

Reference 69

Resolution: unresolved; no resolver link, observed 2026-08-06T20:14:26.634219Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e392ee3c-fb5c-481c-9615-e62c0bd6c656 · inbound

Attention Slipping: A Mechanistic Understanding of Jailbreak Attacks and Defenses in LLMs cites this paper.

Attention Slipping: A Mechanistic Understanding of Jailbreak Attacks and Defenses in LLMs Low-Resource Languages Jailbreak GPT-4

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-06T19:54:11.798190Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 70640b84-e213-4601-b2c0-aa0b955aa74c · inbound

CAVGAN: Unifying Jailbreak and Defense of LLMs via Generative Adversarial Attacks on their Internal Representations cites this paper.

CAVGAN: Unifying Jailbreak and Defense of LLMs via Generative Adversarial Attacks on their Internal Representations Low-Resource Languages Jailbreak GPT-4

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-06T19:18:46.549467Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f7ee0b76-e1ea-426c-b837-ad7777a81516 · inbound

Circumventing Safety Alignment in Large Language Models Through Embedding Space Toxicity Attenuation cites this paper.

Circumventing Safety Alignment in Large Language Models Through Embedding Space Toxicity Attenuation Low-Resource Languages Jailbreak GPT-4

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-06T19:26:13.755908Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ddf51fb8-ea69-4843-b656-286c1056e48d · inbound

SEALGuard: Safeguarding the Multilingual Conversations in Southeast Asian Languages for LLM Software Systems cites this paper.

SEALGuard: Safeguarding the Multilingual Conversations in Southeast Asian Languages for LLM Software Systems Low-Resource Languages Jailbreak GPT-4

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-06T18:28:46.143521Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 015af25f-f1e0-4a56-bfe7-fea6ed1beb49 · inbound

PRM-Free Security Alignment of Large Models via Red Teaming and Adversarial Training cites this paper.

PRM-Free Security Alignment of Large Models via Red Teaming and Adversarial Training Low-Resource Languages Jailbreak GPT-4

Reference 89

Resolution: unresolved; no resolver link, observed 2026-08-06T17:35:48.582594Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fd092592-9b9a-45b2-b9c7-b628184385d1 · inbound

Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text Generation cites this paper.

Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text Generation Low-Resource Languages Jailbreak GPT-4

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-05T20:31:38.034933Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ea933e5c-774d-4f3e-af84-07d901cd2ee6 · inbound

On Surjectivity of Neural Networks: Can you elicit any behavior from your model? cites this paper.

On Surjectivity of Neural Networks: Can you elicit any behavior from your model? Low-Resource Languages Jailbreak GPT-4

Reference 109

Resolution: unresolved; no resolver link, observed 2026-08-05T16:00:52.265295Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a0678564-32d8-4534-93d4-5716c60d3a32 · inbound

JADES: A Universal Framework for Jailbreak Assessment via Decompositional Scoring cites this paper.

JADES: A Universal Framework for Jailbreak Assessment via Decompositional Scoring Low-Resource Languages Jailbreak GPT-4

Reference 61

Resolution: unresolved; no resolver link, observed 2026-08-05T14:51:03.803021Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a969486c-572c-44f7-aaab-60fbad43883b · inbound

AntiDote: Bi-level Adversarial Training for Tamper-Resistant LLMs cites this paper.

AntiDote: Bi-level Adversarial Training for Tamper-Resistant LLMs Low-Resource Languages Jailbreak GPT-4

Reference 89

Resolution: unresolved; no resolver link, observed 2026-08-15T16:25:35.748405Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a3a9ec3b-aa08-4e34-92ef-7fe2bdb95827 · inbound

SoK: Systematizing LLM Prompt Security: Taxonomies, Datasets, and Unified Evaluation of Attacks and Defenses cites this paper.

SoK: Systematizing LLM Prompt Security: Taxonomies, Datasets, and Unified Evaluation of Attacks and Defenses Low-Resource Languages Jailbreak GPT-4

Reference 219

Resolution: unresolved; no resolver link, observed 2026-08-04T09:25:58.150266Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 557b2729-488e-4a06-986c-0e27793bd88f · inbound

ASTRA: An Automated Framework for Strategy Discovery, Retrieval, and Evolution for Jailbreaking LLMs cites this paper.

ASTRA: An Automated Framework for Strategy Discovery, Retrieval, and Evolution for Jailbreaking LLMs Low-Resource Languages Jailbreak GPT-4

Reference 54

Resolution: verified exact; local_arxiv, observed 2026-05-18T01:55:37.975623Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 0a168ba9-4614-456a-b49b-c1513d2e07a0 · inbound

SelfGrader: LLM Jailbreak Detection via Anchored Token-Level Logits cites this paper.

SelfGrader: LLM Jailbreak Detection via Anchored Token-Level Logits Low-Resource Languages Jailbreak GPT-4

Reference 26

Resolution: verified exact; arxiv_id, observed 2026-05-17T09:24:14.203470Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation e9833494-62af-4690-86b2-ec0dcd530029 · inbound

TEMPLATEFUZZ: Fine-Grained Chat Template Fuzzing for Jailbreaking and Red Teaming LLMs cites this paper.

TEMPLATEFUZZ: Fine-Grained Chat Template Fuzzing for Jailbreaking and Red Teaming LLMs Low-Resource Languages Jailbreak GPT-4

Reference 59

Resolution: verified exact; arxiv_id, observed 2026-05-17T09:24:14.203470Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation e075710c-92a5-4d79-8e88-d7f33173d648 · inbound

LASA: Language-Agnostic Semantic Alignment at the Semantic Bottleneck for LLM Safety cites this paper.

LASA: Language-Agnostic Semantic Alignment at the Semantic Bottleneck for LLM Safety Low-Resource Languages Jailbreak GPT-4

Reference 3

Resolution: metadata mismatch; arxiv_id, observed 2026-05-17T09:24:14.203470Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 6c23ba0a-308f-48a1-9558-2eea7772ee62 · inbound

COMPASS: COntinual Multilingual PEFT with Adaptive Semantic Sampling cites this paper.

COMPASS: COntinual Multilingual PEFT with Adaptive Semantic Sampling Low-Resource Languages Jailbreak GPT-4

Reference 82

Resolution: verified exact; arxiv_id, observed 2026-05-17T09:24:14.203470Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 7ee8a589-60cd-426c-bbe5-c1aace63aa1b · inbound

Automation-Exploit: A Multi-Agent LLM Framework for Adaptive Offensive Security with Digital Twin-Based Risk-Mitigated Exploitation cites this paper.

Automation-Exploit: A Multi-Agent LLM Framework for Adaptive Offensive Security with Digital Twin-Based Risk-Mitigated Exploitation Low-Resource Languages Jailbreak GPT-4

Reference 47

Resolution: verified exact; arxiv_id, observed 2026-05-17T09:24:14.203470Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 1a14223e-619f-4373-9e0e-8f1d3e813f72 · inbound

Attention Is Where You Attack cites this paper.

Attention Is Where You Attack Low-Resource Languages Jailbreak GPT-4

Reference 15

Resolution: verified exact; arxiv_id, observed 2026-05-17T09:24:14.203470Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 1e51af16-11b0-450e-93af-2e7b0e919c8b · inbound

A Theoretical Game of Attacks via Compositional Skills cites this paper.

A Theoretical Game of Attacks via Compositional Skills Low-Resource Languages Jailbreak GPT-4

Reference 16

Resolution: verified exact; arxiv_id, observed 2026-05-17T09:24:14.203470Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation db57c284-d282-44e8-8613-4e3b15a9fb7e · inbound

Multilingual Safety Alignment via Self-Distillation cites this paper.

Multilingual Safety Alignment via Self-Distillation Low-Resource Languages Jailbreak GPT-4

Reference 18

Resolution: metadata mismatch; arxiv_id, observed 2026-05-17T09:24:14.203470Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 3b739871-9309-4df5-80c6-7e6a5f004c0d · inbound

Multilingual Safety Alignment via Self-Distillation cites this paper.

Multilingual Safety Alignment via Self-Distillation Low-Resource Languages Jailbreak GPT-4

Reference 18

Resolution: metadata mismatch; arxiv_id, observed 2026-05-17T09:24:14.203470Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 1d09e206-3ed3-49f3-b659-baae2f5652be · inbound

Redefining AI Red Teaming in the Agentic Era: From Weeks to Hours cites this paper.

Redefining AI Red Teaming in the Agentic Era: From Weeks to Hours Low-Resource Languages Jailbreak GPT-4

Reference 21

Resolution: verified exact; arxiv_id, observed 2026-05-17T09:24:14.203470Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 88731c6b-a13a-4b79-bd28-2d68ae420da2 · inbound

One Turn Too Late: Response-Aware Defense Against Hidden Malicious Intent in Multi-Turn Dialogue cites this paper.

One Turn Too Late: Response-Aware Defense Against Hidden Malicious Intent in Multi-Turn Dialogue Low-Resource Languages Jailbreak GPT-4

Reference 37

Resolution: verified exact; arxiv_id, observed 2026-05-17T09:24:14.203470Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation b6d226c8-474d-485d-90d1-cdd3e69bc946 · inbound

One Turn Too Late: Response-Aware Defense Against Hidden Malicious Intent in Multi-Turn Dialogue cites this paper.

One Turn Too Late: Response-Aware Defense Against Hidden Malicious Intent in Multi-Turn Dialogue Low-Resource Languages Jailbreak GPT-4

Reference 37

Resolution: verified exact; arxiv_id, observed 2026-05-17T09:24:14.203470Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation a30bdb1c-f63e-4508-bb95-f4f20759d76c · inbound

Few-Shot Truly Benign DPO Attack for Jailbreaking LLMs cites this paper.

Few-Shot Truly Benign DPO Attack for Jailbreaking LLMs Low-Resource Languages Jailbreak GPT-4

Reference 5

Resolution: metadata mismatch; arxiv_id, observed 2026-05-17T09:24:14.203470Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation e5133c3d-5357-48e3-98d0-2801510da929 · inbound

Certified Robustness under Heterogeneous Perturbations via Hybrid Randomized Smoothing cites this paper.

Certified Robustness under Heterogeneous Perturbations via Hybrid Randomized Smoothing Low-Resource Languages Jailbreak GPT-4

Reference 17

Resolution: verified exact; arxiv_id, observed 2026-05-17T09:24:14.203470Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 64eb1c64-7824-44ed-895b-90e5aa7615e0 · inbound

From AI-Generated Content to Agentic Action: Security and Safety Threats in Generative AI cites this paper.

From AI-Generated Content to Agentic Action: Security and Safety Threats in Generative AI Low-Resource Languages Jailbreak GPT-4

Reference 149

Resolution: verified exact; local_arxiv, observed 2026-05-20T18:08:50.503214Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 81ed05c5-27fb-4e8e-8bcf-36d042269f9b · inbound

Multilingual jailbreaking of LLMs using low-resource languages cites this paper.

Multilingual jailbreaking of LLMs using low-resource languages Low-Resource Languages Jailbreak GPT-4

Reference 8

Resolution: metadata mismatch; local_arxiv, observed 2026-05-20T10:33:12.153016Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 5f91e606-6411-494d-b76b-97e309ba57d0 · inbound

LASH: Adaptive Semantic Hybridization for Black-Box Jailbreaking of Large Language Models cites this paper.

LASH: Adaptive Semantic Hybridization for Black-Box Jailbreaking of Large Language Models Low-Resource Languages Jailbreak GPT-4

Reference 36

Resolution: verified exact; local_arxiv, observed 2026-05-21T04:49:35.465825Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 3c8e8c2d-22da-4878-818e-c73a971c8684 · inbound

SomaliBench Eval: Measuring English-to-Somali Refusal Gaps in Open-Weight Language Models cites this paper.

SomaliBench Eval: Measuring English-to-Somali Refusal Gaps in Open-Weight Language Models Low-Resource Languages Jailbreak GPT-4

Reference 12

Resolution: verified exact; local_arxiv, observed 2026-06-29T22:34:01.325996Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation d4844bf5-f01b-4adb-acfa-fe29f720b1a3 · inbound

Evolving Skill-Structured Attack Memory Enhances LLM Jailbreaking cites this paper.

Evolving Skill-Structured Attack Memory Enhances LLM Jailbreaking Low-Resource Languages Jailbreak GPT-4

Reference 8

Resolution: metadata mismatch; local_arxiv, observed 2026-06-29T07:13:16.290123Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation f0e5f82d-8fb4-4c90-945d-3324333f93d9 · inbound

Low-Resource Safety Failures Are Action Failures, Not Representation Failures cites this paper.

Low-Resource Safety Failures Are Action Failures, Not Representation Failures Low-Resource Languages Jailbreak GPT-4

Reference 17

Resolution: verified exact; local_arxiv, observed 2026-06-28T17:02:24.050953Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 851b7c7a-e4ef-49d9-8c90-c4f5eb351590 · inbound

Implicit Geographic Inference in LLM Medical Triage: Language-Driven Disparities in Emergency Recommendations cites this paper.

Implicit Geographic Inference in LLM Medical Triage: Language-Driven Disparities in Emergency Recommendations Low-Resource Languages Jailbreak GPT-4

Reference 11

Resolution: metadata mismatch; local_arxiv, observed 2026-06-28T17:02:24.386957Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 9d2e5706-ef58-49f8-8c6a-a8215af88a7d · inbound

Inference-Time Vulnerability Beyond Shallow Safety: Alignment Along Generation Trajectories cites this paper.

Inference-Time Vulnerability Beyond Shallow Safety: Alignment Along Generation Trajectories Low-Resource Languages Jailbreak GPT-4

Reference 3

Resolution: malformed identifier; local_arxiv, observed 2026-07-02T08:26:47.879196Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 876a4ca2-4fe7-4d9b-9814-3d24ef178c63 · inbound

CHASE: Adversarial Red-Blue Teaming for Improving LLM Safety using Reinforcement Learning cites this paper.

CHASE: Adversarial Red-Blue Teaming for Improving LLM Safety using Reinforcement Learning Low-Resource Languages Jailbreak GPT-4

Reference 1

Resolution: verified exact; local_arxiv, observed 2026-07-02T12:06:55.641922Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 0ca34582-8e8d-4677-8e07-024afe7f940c · inbound

SlotGCG: Exploiting the Positional Vulnerability in LLMs for Jailbreak Attacks cites this paper.

SlotGCG: Exploiting the Positional Vulnerability in LLMs for Jailbreak Attacks Low-Resource Languages Jailbreak GPT-4

Reference 30

Resolution: metadata mismatch; local_arxiv, observed 2026-07-02T13:26:59.338990Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 3dde908f-93b3-4a35-86e7-dcaa763179da · inbound

Defending Jailbreak Attacks on Large Language Models via Manifold Trajectory Kinetics cites this paper.

Defending Jailbreak Attacks on Large Language Models via Manifold Trajectory Kinetics Low-Resource Languages Jailbreak GPT-4

Reference 72

Resolution: verified exact; local_arxiv, observed 2026-07-02T17:37:14.905991Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 30fbb572-a222-46f2-bcf6-90395448acc2 · inbound

Safety is Contextual, LLM-Judges Are Not: Navigating the Rigid Priors of Evaluators cites this paper.

Safety is Contextual, LLM-Judges Are Not: Navigating the Rigid Priors of Evaluators Low-Resource Languages Jailbreak GPT-4

Reference 33

Resolution: metadata mismatch; local_arxiv, observed 2026-06-27T21:41:18.502143Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 869b28d2-4ea0-40a9-b7e0-ca0b14518301 · inbound

Culturally-Adapted Red-Teaming Across East and Southeast Asian Contexts: A Methodological and Comparative Analysis cites this paper.

Culturally-Adapted Red-Teaming Across East and Southeast Asian Contexts: A Methodological and Comparative Analysis Low-Resource Languages Jailbreak GPT-4

Reference 15

Resolution: verified exact; local_arxiv, observed 2026-07-03T01:07:30.331495Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 3c35fb39-c1c1-4144-8e43-6bb0965f3bf2 · inbound

Grammar-Constrained Decoding Can Jailbreak LLMs into Generating Malicious Code cites this paper.

Grammar-Constrained Decoding Can Jailbreak LLMs into Generating Malicious Code Low-Resource Languages Jailbreak GPT-4

Reference 39

Resolution: verified exact; local_arxiv, observed 2026-07-03T11:58:06.191553Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 87300ae7-8f77-4c6c-9b13-c244b35237bf · inbound

PHANTOM: A Large-Scale Dataset of Multimodal Adversarial Attacks for Vision-Language Models cites this paper.

PHANTOM: A Large-Scale Dataset of Multimodal Adversarial Attacks for Vision-Language Models Low-Resource Languages Jailbreak GPT-4

Reference 52

Resolution: verified exact; local_arxiv, observed 2026-07-04T17:09:59.495564Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation ae8e0d9e-e5ae-4280-8be1-391f641c46f5 · inbound

A Red Teaming Framework for Large Language Models: A Case Study on Faithfulness Evaluation cites this paper.

A Red Teaming Framework for Large Language Models: A Case Study on Faithfulness Evaluation Low-Resource Languages Jailbreak GPT-4

Reference 33

Resolution: metadata mismatch; local_arxiv, observed 2026-07-04T19:50:11.071589Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 4b18ef6e-a960-4f42-ad66-af71683a75e7 · inbound

A Red Teaming Framework for Large Language Models: A Case Study on Faithfulness Evaluation cites this paper.

A Red Teaming Framework for Large Language Models: A Case Study on Faithfulness Evaluation Low-Resource Languages Jailbreak GPT-4

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-02T10:16:38.577010Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b8b7a5d9-06d6-497d-ac9b-cd082d2e9672 · inbound

Mitigating Taint-Style Vulnerabilities in MCP Servers via Security-Aware Tool Descriptions cites this paper.

Mitigating Taint-Style Vulnerabilities in MCP Servers via Security-Aware Tool Descriptions Low-Resource Languages Jailbreak GPT-4

Reference 64

Resolution: verified exact; local_arxiv, observed 2026-07-09T10:26:11.124368Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 22beb086-42d9-4e21-83f2-1bb05cbe5467 · inbound

Safety That Does Not Transfer: Cross-Lingual Clinical Correctness Drift in Deployable Medical Language Models cites this paper.

Safety That Does Not Transfer: Cross-Lingual Clinical Correctness Drift in Deployable Medical Language Models Low-Resource Languages Jailbreak GPT-4

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-01T18:33:08.006467Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4b4f6118-97a6-4bab-b21e-601db75eb50f · inbound

QuantiBias: Benchmarking Quantization-Induced Bias in LLMs cites this paper.

QuantiBias: Benchmarking Quantization-Induced Bias in LLMs Low-Resource Languages Jailbreak GPT-4

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-01T08:38:56.164741Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8e123e44-bafe-4111-ac4e-b8a13c14c091 · inbound

Inspect India Evals: An Open Benchmarking Framework for Evaluating Large Language Models in the Indian Linguistic and Cultural Context cites this paper.

Inspect India Evals: An Open Benchmarking Framework for Evaluating Large Language Models in the Indian Linguistic and Cultural Context Low-Resource Languages Jailbreak GPT-4

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-01T02:40:45.091898Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation da228762-a317-4082-a49b-946363d9df69 · inbound

Same violence, different answer: how AI responds to coercive control against women across languages cites this paper.

Same violence, different answer: how AI responds to coercive control against women across languages Low-Resource Languages Jailbreak GPT-4

Reference 2018

Resolution: unresolved; no resolver link, observed 2026-08-06T00:14:01.267746Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 71d8efd2-22c5-40c3-b32e-9750cd307da2 · inbound

Single Canonical Prompts Underestimate LLM Safety's Surface-Form Sensitivity cites this paper.

Single Canonical Prompts Underestimate LLM Safety's Surface-Form Sensitivity Low-Resource Languages Jailbreak GPT-4

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-05T00:48:49.383630Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d5e71f74-3316-4a22-91b4-87fd5cdccce7 · inbound

Cross-Lingual Bias in Large Language Models: A Comparative Analysis of English and Swahili cites this paper.

Cross-Lingual Bias in Large Language Models: A Comparative Analysis of English and Swahili Low-Resource Languages Jailbreak GPT-4

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-05T17:11:46.281928Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 99a6199e-6ae3-40ec-b128-1a5692750599 · inbound

Who Bridges Safety? Identifying and Targeting Cross-Lingual Shared Safety Pathways cites this paper.

Who Bridges Safety? Identifying and Targeting Cross-Lingual Shared Safety Pathways Low-Resource Languages Jailbreak GPT-4

Reference 73

Resolution: unresolved; no resolver link, observed 2026-08-11T23:44:39.628652Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 749fd45f-f6c6-445f-80e0-106a461a5a3b · inbound

From Values to Benchmarks: Evaluating Large Language Models for Governmental Use in Dutch cites this paper.

From Values to Benchmarks: Evaluating Large Language Models for Governmental Use in Dutch Low-Resource Languages Jailbreak GPT-4

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-11T04:15:50.149734Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.