Paper Citation Record · LEDGER

BadLingual: A Novel Lingual-Backdoor Attack against Large Language Models

As of 16 August 2026, this Paper Citation Record lists 67 of 67 outbound references and 1 inbound Pith citation observation for arXiv:2505.03501.

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

pith.paper-citation-record.v1
2505.03501 v1

Coverage vector

measured 67 of 67 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-15T23:54:42.882112Z

measured 68 of 68 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-16T06:30:59.297886+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-06-29T23:51:05.413122Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-06-29T23:54:03.327253Z

Reference resolution

67 of 67 outbound references displayed

verified exact0
verified fuzzy37
unresolved30
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 36508047-276b-4be3-94b4-4bf4c731fed0 · outbound

This paper cites https://claude.ai/.

BadLingual: A Novel Lingual-Backdoor Attack against Large Language Models https://claude.ai/

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:54:43.692700Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 32e10651-fc18-42b2-856c-115d64cfeb46 · outbound

This paper cites https://huggingface.co/deepseek-ai/ DeepSeek-V3.

BadLingual: A Novel Lingual-Backdoor Attack against Large Language Models https://huggingface.co/deepseek-ai/ DeepSeek-V3

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:54:43.681058Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation ce258388-f9b2-4811-9aad-2153b77066eb · outbound

This paper cites https://flageval.baai.ac.cn/.

BadLingual: A Novel Lingual-Backdoor Attack against Large Language Models https://flageval.baai.ac.cn/

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:54:43.669166Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 39145733-adf6-4f7f-8f39-724bb5d091fb · outbound

This paper cites https://gemini.google.com/app.

BadLingual: A Novel Lingual-Backdoor Attack against Large Language Models https://gemini.google.com/app

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:54:43.657547Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation fb552c42-181d-49b4-b39e-b9c61d850445 · outbound

This paper cites https://en.wikipedia.org/wiki/List_of_ languages_by_total_number_of_speakers.

BadLingual: A Novel Lingual-Backdoor Attack against Large Language Models https://en.wikipedia.org/wiki/List_of_ languages_by_total_number_of_speakers

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:54:43.646013Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 0c82ffba-6011-46f5-b9ec-f385f41815cb · outbound

This paper cites https://huggingface.

BadLingual: A Novel Lingual-Backdoor Attack against Large Language Models https://huggingface

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:54:43.633929Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation e9a383df-f545-4d0d-aa7c-fb7399271af8 · outbound

This paper cites https://huggingface.co/datasets/ lighteval/siqa.

BadLingual: A Novel Lingual-Backdoor Attack against Large Language Models https://huggingface.co/datasets/ lighteval/siqa

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:54:43.621271Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 5d2a04d3-ea4b-4054-bd1c-0a04b40e25c7 · outbound

This paper cites Mega: Multilingual evaluation of generative ai, 2023.

BadLingual: A Novel Lingual-Backdoor Attack against Large Language Models Mega: Multilingual evaluation of generative ai, 2023

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:54:43.608193Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation cc729828-e39f-4df2-9383-a897f33196f6 · outbound

This paper cites Palm 2 technical report, 2023.

BadLingual: A Novel Lingual-Backdoor Attack against Large Language Models Palm 2 technical report, 2023

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:54:43.596192Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation c634c9b2-d55d-4f03-baef-a646a0a4c268 · outbound

This paper cites Piqa: Reasoning about physical commonsense in natural language.

BadLingual: A Novel Lingual-Backdoor Attack against Large Language Models Piqa: Reasoning about physical commonsense in natural language

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:54:43.584309Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation e823aa29-4bcd-484e-881a-b6fa24fa6242 · outbound

This paper cites Language models are few-shot learners.

BadLingual: A Novel Lingual-Backdoor Attack against Large Language Models Language models are few-shot learners

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:54:43.572582Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation ef8a88d5-db74-4e28-91ef-56f7cc439262 · outbound

This paper cites Multi-turn hidden backdoor in large lan- guage model-powered chatbot models.

BadLingual: A Novel Lingual-Backdoor Attack against Large Language Models Multi-turn hidden backdoor in large lan- guage model-powered chatbot models

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:54:43.559865Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 5fc8552d-1481-4e22-af5b-4a86f7ca9a67 · outbound

This paper cites BadPre: Task-agnostic Backdoor Attacks to Pre-trained NLP Foundation Models.

BadLingual: A Novel Lingual-Backdoor Attack against Large Language Models BadPre: Task-agnostic Backdoor Attacks to Pre-trained NLP Foundation Models

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-15T23:54:42.686197Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d3c17924-a070-48c9-b0b0-4dc1571a4cf4 · outbound

This paper cites Stealthy and Persistent Unalignment on Large Language Models via Backdoor Injections.

BadLingual: A Novel Lingual-Backdoor Attack against Large Language Models Stealthy and Persistent Unalignment on Large Language Models via Backdoor Injections

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-15T23:54:42.690260Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 296e37fd-550d-4507-86dc-68e4fd2162e2 · outbound

This paper cites Badnl: Backdoor attacks against nlp models with semantic-preserving im- provements.

BadLingual: A Novel Lingual-Backdoor Attack against Large Language Models Badnl: Backdoor attacks against nlp models with semantic-preserving im- provements

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:54:43.547481Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 94b0a6cb-9c22-430f-aba8-9767b38aff58 · outbound

This paper cites Palm: Scaling language modeling with pathways.

BadLingual: A Novel Lingual-Backdoor Attack against Large Language Models Palm: Scaling language modeling with pathways

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:54:43.534734Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation a2246d47-a432-4dd1-b1b8-efb8d580b4aa · outbound

This paper cites Boolq: Exploring the surprising difficulty of natural yes/no questions.

BadLingual: A Novel Lingual-Backdoor Attack against Large Language Models Boolq: Exploring the surprising difficulty of natural yes/no questions

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:54:43.522342Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 8cb53e02-f088-475a-aa63-2c875359f751 · outbound

This paper cites Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge.

BadLingual: A Novel Lingual-Backdoor Attack against Large Language Models Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-15T23:54:42.704520Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 057971c5-bfd6-46c2-b573-03dc7d647690 · outbound

This paper cites Training Verifiers to Solve Math Word Problems.

BadLingual: A Novel Lingual-Backdoor Attack against Large Language Models Training Verifiers to Solve Math Word Problems

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-15T23:54:42.708075Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 68f0d474-a6a2-4edb-be08-ea10afdf7caa · outbound

This paper cites Cross- lingual language model pretraining.

BadLingual: A Novel Lingual-Backdoor Attack against Large Language Models Cross- lingual language model pretraining

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:54:43.509098Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation aabd96a2-7e98-417d-a7d4-2d7a7d36d857 · outbound

This paper cites Opencompass: A universal evaluation platform for foundation models.

BadLingual: A Novel Lingual-Backdoor Attack against Large Language Models Opencompass: A universal evaluation platform for foundation models

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:54:43.496277Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 41bb24b1-2538-4bde-ba08-e94ab57f81fa · outbound

This paper cites A unified evaluation of textual backdoor learning: Frameworks and benchmarks.

BadLingual: A Novel Lingual-Backdoor Attack against Large Language Models A unified evaluation of textual backdoor learning: Frameworks and benchmarks

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:54:43.483986Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation ea9a1a17-cd12-4cca-8dea-198642b79f7d · outbound

This paper cites A back- door attack against lstm-based text classification sys- tems.

BadLingual: A Novel Lingual-Backdoor Attack against Large Language Models A back- door attack against lstm-based text classification sys- tems

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:54:43.472005Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 7e7f677a-ff21-4284-9f1f-4c0c7a592725 · outbound

This paper cites Deepseek llm: Scaling open-source language models with longtermism, 2024.

BadLingual: A Novel Lingual-Backdoor Attack against Large Language Models Deepseek llm: Scaling open-source language models with longtermism, 2024

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:54:43.459668Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 24c8462e-739a-4011-bdbb-e5635edd0889 · outbound

This paper cites Multilingual Jailbreak Challenges in Large Language Models.

BadLingual: A Novel Lingual-Backdoor Attack against Large Language Models Multilingual Jailbreak Challenges in Large Language Models

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-15T23:54:42.730085Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ac473e4d-0697-45a8-86fe-db280e4f0822 · outbound

This paper cites BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding.

BadLingual: A Novel Lingual-Backdoor Attack against Large Language Models BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-15T23:54:42.737570Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ff88102f-4440-46ba-8046-e5a0048be711 · outbound

This paper cites Chatglm: A family of large language models from glm-130b to glm- 4 all tools, 2024.

BadLingual: A Novel Lingual-Backdoor Attack against Large Language Models Chatglm: A family of large language models from glm-130b to glm- 4 all tools, 2024

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:54:43.447948Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 4d6673c1-307e-4051-bbf1-f9043416150d · outbound

This paper cites Explaining and Harnessing Adversarial Examples.

BadLingual: A Novel Lingual-Backdoor Attack against Large Language Models Explaining and Harnessing Adversarial Examples

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-15T23:54:42.744127Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4fc44a55-9055-4bc6-9951-11a6c4e921b0 · outbound

This paper cites The llama 3 herd of models, 2024.

BadLingual: A Novel Lingual-Backdoor Attack against Large Language Models The llama 3 herd of models, 2024

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-15T23:54:42.747801Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 905e04a7-3aa0-4767-b5ab-27e8cd475eb6 · outbound

This paper cites BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chain.

BadLingual: A Novel Lingual-Backdoor Attack against Large Language Models BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chain

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-15T23:54:42.751300Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cdd74825-6d34-48e5-a2d3-563fcb6efb5f · outbound

This paper cites Backdooring multimodal learning.

BadLingual: A Novel Lingual-Backdoor Attack against Large Language Models Backdooring multimodal learning

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:54:43.429929Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 77dee6a7-6ba6-4527-8886-9f9960c15f9b · outbound

This paper cites Exploring Backdoor Vulnerabilities of Chat Models.

BadLingual: A Novel Lingual-Backdoor Attack against Large Language Models Exploring Backdoor Vulnerabilities of Chat Models

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-15T23:54:42.758170Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3140c0ba-47e8-4314-9a26-cfa34557419e · outbound

This paper cites LoRA: Low-Rank Adaptation of Large Language Models.

BadLingual: A Novel Lingual-Backdoor Attack against Large Language Models LoRA: Low-Rank Adaptation of Large Language Models

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-15T23:54:42.762097Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a90ba68c-c773-4a0a-868d-b976a25fa1eb · outbound

This paper cites Composite Backdoor Attacks Against Large Language Models.

BadLingual: A Novel Lingual-Backdoor Attack against Large Language Models Composite Backdoor Attacks Against Large Language Models

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-15T23:54:42.765568Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ffcf8c07-4c09-4f92-bd02-faf36f600a02 · outbound

This paper cites Backdoor Attacks for In-Context Learning with Language Models.

BadLingual: A Novel Lingual-Backdoor Attack against Large Language Models Backdoor Attacks for In-Context Learning with Language Models

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-15T23:54:42.769109Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5c0b90f2-b7b7-4924-b5f2-0ba5053feb72 · outbound

This paper cites BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension.

BadLingual: A Novel Lingual-Backdoor Attack against Large Language Models BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-15T23:54:42.772707Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f02cb15a-80ca-49fc-b7c0-f79215de2580 · outbound

This paper cites Eliciting the translation ability of large language models via multilingual finetuning with translation instructions.

BadLingual: A Novel Lingual-Backdoor Attack against Large Language Models Eliciting the translation ability of large language models via multilingual finetuning with translation instructions

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:54:43.416537Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation c3a07333-32e5-4598-9fab-f0f440597a4a · outbound

This paper cites Hid- den backdoors in human-centric language models.

BadLingual: A Novel Lingual-Backdoor Attack against Large Language Models Hid- den backdoors in human-centric language models

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:54:43.403886Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation d443d7d6-a92a-49e2-b9ba-cb3b16c35a33 · outbound

This paper cites Faster-GCG: Efficient Discrete Optimization Jailbreak Attacks against Aligned Large Language Models.

BadLingual: A Novel Lingual-Backdoor Attack against Large Language Models Faster-GCG: Efficient Discrete Optimization Jailbreak Attacks against Aligned Large Language Models

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-15T23:54:42.783670Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 628fe84c-8ec4-4550-aa94-da02ecb0e4e6 · outbound

This paper cites BadEdit: Backdooring large language models by model editing.

BadLingual: A Novel Lingual-Backdoor Attack against Large Language Models BadEdit: Backdooring large language models by model editing

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-15T23:54:42.787131Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 95526912-2fd9-4673-a2a5-6e838119e6b2 · outbound

This paper cites Backdoor learning: A survey.

BadLingual: A Novel Lingual-Backdoor Attack against Large Language Models Backdoor learning: A survey

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-15T23:54:42.791135Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5a6db6ba-f356-4aef-9c42-b0737b1220ef · outbound

This paper cites Rouge: A package for automatic evalua- tion of summaries.

BadLingual: A Novel Lingual-Backdoor Attack against Large Language Models Rouge: A package for automatic evalua- tion of summaries

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:54:43.385085Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation ea58c216-397a-482f-b276-1d4a134f4490 · outbound

This paper cites Towards Deep Learning Models Resistant to Adversarial Attacks.

BadLingual: A Novel Lingual-Backdoor Attack against Large Language Models Towards Deep Learning Models Resistant to Adversarial Attacks

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-15T23:54:42.797895Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6b4e56ee-4a41-4364-8eb7-98855dbb434f · outbound

This paper cites Gpt-4o system card, 2024.

BadLingual: A Novel Lingual-Backdoor Attack against Large Language Models Gpt-4o system card, 2024

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-15T23:54:42.801492Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 35f507b3-023d-4a68-a667-5c6271e2f827 · outbound

This paper cites ERNIE-M: Enhanced Multilingual Representation by Aligning Cross-lingual Semantics with Monolingual Corpora.

BadLingual: A Novel Lingual-Backdoor Attack against Large Language Models ERNIE-M: Enhanced Multilingual Representation by Aligning Cross-lingual Semantics with Monolingual Corpora

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-15T23:54:42.804862Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a8019bac-139c-430d-ac30-aec42051d526 · outbound

This paper cites Hidden trigger backdoor attack on{NLP} models via linguistic style manipulation.

BadLingual: A Novel Lingual-Backdoor Attack against Large Language Models Hidden trigger backdoor attack on{NLP} models via linguistic style manipulation

Reference 48

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:54:43.366612Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 886912dd-0872-4e1d-8ce8-54eb1eae78b2 · outbound

This paper cites ONION: A Simple and Effective Defense Against Textual Backdoor Attacks.

BadLingual: A Novel Lingual-Backdoor Attack against Large Language Models ONION: A Simple and Effective Defense Against Textual Backdoor Attacks

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-15T23:54:42.811753Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b270ec18-6233-48ab-b9e5-62e4ee7f5fef · outbound

This paper cites Mind the Style of Text! Adversarial and Backdoor Attacks Based on Text Style Transfer.

BadLingual: A Novel Lingual-Backdoor Attack against Large Language Models Mind the Style of Text! Adversarial and Backdoor Attacks Based on Text Style Transfer

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-15T23:54:42.815327Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0a2caea1-d126-49d5-bf26-80685ba9243b · outbound

This paper cites Hidden Killer: Invisible Textual Backdoor Attacks with Syntactic Trigger.

BadLingual: A Novel Lingual-Backdoor Attack against Large Language Models Hidden Killer: Invisible Textual Backdoor Attacks with Syntactic Trigger

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-15T23:54:42.819091Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 56be8b6c-56d5-4c85-8767-6d90311c6770 · outbound

This paper cites Multilingual Large Language Model: A Survey of Resources, Taxonomy and Frontiers.

BadLingual: A Novel Lingual-Backdoor Attack against Large Language Models Multilingual Large Language Model: A Survey of Resources, Taxonomy and Frontiers

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-15T23:54:42.822730Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ca755f1c-f6bd-40db-b716-1a6b1c9ddb0f · outbound

This paper cites Qwen2.5 techni- cal report, 2025.

BadLingual: A Novel Lingual-Backdoor Attack against Large Language Models Qwen2.5 techni- cal report, 2025

Reference 53

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:54:43.354788Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 6b23ec19-b51a-4c56-a796-cc08a313ea73 · outbound

This paper cites Mathematical discoveries from program search with large language models.

BadLingual: A Novel Lingual-Backdoor Attack against Large Language Models Mathematical discoveries from program search with large language models

Reference 54

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:54:43.343591Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 89eadeaa-9cab-4448-8b96-80fc10bd3b4e · outbound

This paper cites Recursive deep models for semantic composi- tionality over a sentiment treebank.

BadLingual: A Novel Lingual-Backdoor Attack against Large Language Models Recursive deep models for semantic composi- tionality over a sentiment treebank

Reference 55

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:54:43.332050Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 2e650baf-7a73-4ba1-ac33-a492afe0d4f1 · outbound

This paper cites CommonsenseQA: A question answer- ing challenge targeting commonsense knowledge.

BadLingual: A Novel Lingual-Backdoor Attack against Large Language Models CommonsenseQA: A question answer- ing challenge targeting commonsense knowledge

Reference 56

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:54:43.320484Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation c8ae174c-c878-48f4-aa80-6ef9180419f2 · outbound

This paper cites Multilingual Translation with Extensible Multilingual Pretraining and Finetuning.

BadLingual: A Novel Lingual-Backdoor Attack against Large Language Models Multilingual Translation with Extensible Multilingual Pretraining and Finetuning

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-15T23:54:42.839969Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d2586d70-d36d-4bdb-abce-0ce65cc295a5 · outbound

This paper cites Chain-of-thought prompting elicits reasoning in large language models.

BadLingual: A Novel Lingual-Backdoor Attack against Large Language Models Chain-of-thought prompting elicits reasoning in large language models

Reference 58

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:54:43.309344Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 5bdd73eb-ffba-4c32-a10b-4751c2e6d9ff · outbound

This paper cites PolyLM: An Open Source Polyglot Large Language Model.

BadLingual: A Novel Lingual-Backdoor Attack against Large Language Models PolyLM: An Open Source Polyglot Large Language Model

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-15T23:54:42.847034Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 338e7791-ec7d-46ab-a4d5-6b5a44379d97 · outbound

This paper cites A systematic evaluation of large lan- guage models of code.

BadLingual: A Novel Lingual-Backdoor Attack against Large Language Models A systematic evaluation of large lan- guage models of code

Reference 60

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:54:43.296195Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 0c8c2295-9e95-4a55-a8c8-619ff07e98ee · outbound

This paper cites Backdooring instruction- tuned large language models with virtual prompt in- jection.

BadLingual: A Novel Lingual-Backdoor Attack against Large Language Models Backdooring instruction- tuned large language models with virtual prompt in- jection

Reference 61

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:54:43.283281Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 66f66e94-5a6c-4c2a-814f-96fb8183f98b · outbound

This paper cites Understanding deep learning (still) requires rethinking generalization.

BadLingual: A Novel Lingual-Backdoor Attack against Large Language Models Understanding deep learning (still) requires rethinking generalization

Reference 62

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:54:43.271635Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 8ab6448f-a34c-4c4c-abe9-defd8ae24ff7 · outbound

This paper cites Badmerging: Backdoor attacks against model merging.

BadLingual: A Novel Lingual-Backdoor Attack against Large Language Models Badmerging: Backdoor attacks against model merging

Reference 63

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:54:43.259990Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 917bc08e-67c9-4fda-a03a-47b2ac655c67 · outbound

This paper cites Instruction backdoor attacks against customized LLMs.

BadLingual: A Novel Lingual-Backdoor Attack against Large Language Models Instruction backdoor attacks against customized LLMs

Reference 64

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:54:43.248481Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation c39deb7d-0d0f-43f1-b4f9-59f910a01976 · outbound

This paper cites Instruction tuning for large language models: A survey.

BadLingual: A Novel Lingual-Backdoor Attack against Large Language Models Instruction tuning for large language models: A survey

Reference 65

Resolution: unresolved; no resolver link, observed 2026-08-15T23:54:42.867618Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f92c6622-64e6-4644-8e83-b8b1e425e959 · outbound

This paper cites Character- level convolutional networks for text classification.

BadLingual: A Novel Lingual-Backdoor Attack against Large Language Models Character- level convolutional networks for text classification

Reference 66

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:54:43.236092Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation e16ac32f-7e2a-4f75-97d9-052f517a9c27 · outbound

This paper cites Prompt as Triggers for Backdoor Attack: Examining the Vulnerability in Language Models.

BadLingual: A Novel Lingual-Backdoor Attack against Large Language Models Prompt as Triggers for Backdoor Attack: Examining the Vulnerability in Language Models

Reference 67

Resolution: unresolved; no resolver link, observed 2026-08-15T23:54:42.875457Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 99b9ea69-9b10-476f-aba0-d7613aaa913d · outbound

This paper cites Extrapolating Large Language Models to Non-English by Aligning Languages.

BadLingual: A Novel Lingual-Backdoor Attack against Large Language Models Extrapolating Large Language Models to Non-English by Aligning Languages

Reference 68

Resolution: unresolved; no resolver link, observed 2026-08-15T23:54:42.878852Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ee6d52a9-d60b-49f2-9d91-8742e4e4d091 · outbound

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

BadLingual: A Novel Lingual-Backdoor Attack against Large Language Models Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 69

Resolution: unresolved; no resolver link, observed 2026-08-15T23:54:42.882112Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 70cdb803-1677-418b-9d97-6debabe15e6e · inbound

Security in the Fine-Tuning Lifecycle of Large Language Models: Threats, Defenses,Evaluation, and Future Directions cites this paper.

Security in the Fine-Tuning Lifecycle of Large Language Models: Threats, Defenses,Evaluation, and Future Directions BadLingual: A Novel Lingual-Backdoor Attack against Large Language Models

Reference 75

Resolution: verified exact; arxiv_id, observed 2026-06-29T23:54:03.330778Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.