Paper Citation Record · LEDGER

InfoFlood: Jailbreaking Large Language Models with Information Overload

As of 8 August 2026, this Paper Citation Record lists 42 of 42 outbound references and 1 inbound Pith citation observation for arXiv:2506.12274.

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

pith.paper-citation-record.v1
2506.12274 v1

Coverage vector

measured 42 of 42 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T01:02:31.476445Z

measured 43 of 43 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-08T06:32:00.761636+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-05-18T17:49:42.112564Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-05-18T17:51:41.877221Z

Reference resolution

42 of 42 outbound references displayed

verified exact0
verified fuzzy4
unresolved38
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 4599e56b-8c40-45b2-b42c-c3dafba462cb · outbound

This paper cites write newline.

InfoFlood: Jailbreaking Large Language Models with Information Overload write newline

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-07T01:02:27.992361Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b590bac7-7219-4e38-9bad-ab644bc47292 · outbound

This paper cites Llama 3 model card.

InfoFlood: Jailbreaking Large Language Models with Information Overload Llama 3 model card

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-07T01:02:28.089322Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fb56c737-8c7e-4b8b-a525-fc7ba42f9a2f · outbound

This paper cites Does Refusal Training in LLMs Generalize to the Past Tense?.

InfoFlood: Jailbreaking Large Language Models with Information Overload Does Refusal Training in LLMs Generalize to the Past Tense?

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-07T01:02:28.139129Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 45f4c9b1-61f6-4c56-ac0e-972d3aa5399b · outbound

This paper cites Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks.

InfoFlood: Jailbreaking Large Language Models with Information Overload Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-07T01:02:28.219255Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9955a0d8-e12a-4bdc-96fc-35040173a9e6 · outbound

This paper cites Constitutional AI: Harmlessness from AI Feedback.

InfoFlood: Jailbreaking Large Language Models with Information Overload Constitutional AI: Harmlessness from AI Feedback

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-07T01:02:28.245895Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 73515443-fb14-4a2c-a2b8-88982c43a6ba · outbound

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

InfoFlood: Jailbreaking Large Language Models with Information Overload JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Models

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-07T01:02:28.336517Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a2e4e2fe-c1aa-4c48-88da-f4468050bfcd · outbound

This paper cites Jailbreaking Black Box Large Language Models in Twenty Queries.

InfoFlood: Jailbreaking Large Language Models with Information Overload Jailbreaking Black Box Large Language Models in Twenty Queries

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-07T01:02:28.376924Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 92da5a23-91f1-46d2-80c5-233ed4293158 · outbound

This paper cites JailbreakRadar: Comprehensive Assessment of Jailbreak Attacks Against LLMs.

InfoFlood: Jailbreaking Large Language Models with Information Overload JailbreakRadar: Comprehensive Assessment of Jailbreak Attacks Against LLMs

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-07T01:02:28.442955Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 574d3678-30ed-4795-905f-b9ba33de1454 · outbound

This paper cites Build it Break it Fix it for Dialogue Safety: Robustness from Adversarial Human Attack.

InfoFlood: Jailbreaking Large Language Models with Information Overload Build it Break it Fix it for Dialogue Safety: Robustness from Adversarial Human Attack

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-07T01:02:28.494126Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 473d0749-0446-4e7d-975c-e4f8cee67e56 · outbound

This paper cites Google gemini flash, February 2025.

InfoFlood: Jailbreaking Large Language Models with Information Overload Google gemini flash, February 2025

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T01:02:32.804000Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation a952a564-86e3-4215-84b1-0e5002fc8b9b · outbound

This paper cites Deliberative Alignment: Reasoning Enables Safer Language Models.

InfoFlood: Jailbreaking Large Language Models with Information Overload Deliberative Alignment: Reasoning Enables Safer Language Models

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-07T01:02:28.553458Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 883e1bf8-fe66-41cd-a0e0-11ef0faf44fc · outbound

This paper cites Endless Jailbreaks with Bijection Learning.

InfoFlood: Jailbreaking Large Language Models with Information Overload Endless Jailbreaks with Bijection Learning

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-07T01:02:28.608823Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4a6827c6-57e4-4c4f-b82b-4a02dbd4b8be · outbound

This paper cites Perspective api, 2024.

InfoFlood: Jailbreaking Large Language Models with Information Overload Perspective api, 2024

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T01:02:32.614286Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 9feef088-88b1-411c-a5e0-edf3e581e8f5 · outbound

This paper cites Guard: Role-playing to generate natural-language jailbreakings to test guideline adherence of large language models.

InfoFlood: Jailbreaking Large Language Models with Information Overload Guard: Role-playing to generate natural-language jailbreakings to test guideline adherence of large language models

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-07T01:02:28.827911Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0aaacc26-e9ae-46e3-b432-fb1b3be88750 · outbound

This paper cites Jailbreaking Large Language Models Against Moderation Guardrails via Cipher Characters.

InfoFlood: Jailbreaking Large Language Models with Information Overload Jailbreaking Large Language Models Against Moderation Guardrails via Cipher Characters

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-07T01:02:28.929877Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f29a9c8c-1f44-4a57-a31a-e16b4f2438e7 · outbound

This paper cites Automatically Auditing Large Language Models via Discrete Optimization.

InfoFlood: Jailbreaking Large Language Models with Information Overload Automatically Auditing Large Language Models via Discrete Optimization

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-07T01:02:29.019773Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 65c9f057-029c-4115-b33d-15030852ea12 · outbound

This paper cites DrAttack: Prompt Decomposition and Reconstruction Makes Powerful LLM Jailbreakers.

InfoFlood: Jailbreaking Large Language Models with Information Overload DrAttack: Prompt Decomposition and Reconstruction Makes Powerful LLM Jailbreakers

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-07T01:02:29.162442Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4a430d69-8ffb-4eb8-99a2-165fd2e62582 · outbound

This paper cites AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models.

InfoFlood: Jailbreaking Large Language Models with Information Overload AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-07T01:02:29.259137Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 541aa07d-fcb4-422d-9be6-2c74fe02c0ea · outbound

This paper cites Latent space cartography: Visual analysis of vector space embeddings.

InfoFlood: Jailbreaking Large Language Models with Information Overload Latent space cartography: Visual analysis of vector space embeddings

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T01:02:32.406428Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 6efa3274-449a-4025-b20e-ff89ea5efc74 · outbound

This paper cites Black Box Adversarial Prompting for Foundation Models.

InfoFlood: Jailbreaking Large Language Models with Information Overload Black Box Adversarial Prompting for Foundation Models

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-07T01:02:29.510173Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a809df2a-ab18-47f9-853a-35b55696cd33 · outbound

This paper cites HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal.

InfoFlood: Jailbreaking Large Language Models with Information Overload HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-07T01:02:29.635233Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 24cad203-093f-4e9c-bf12-42058fd26783 · outbound

This paper cites Tree of Attacks: Jailbreaking Black-Box LLMs Automatically.

InfoFlood: Jailbreaking Large Language Models with Information Overload Tree of Attacks: Jailbreaking Black-Box LLMs Automatically

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-07T01:02:29.718383Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 10e19b5b-e007-47c4-bf0a-f615dafda644 · outbound

This paper cites SelfCheck: Using LLMs to Zero-Shot Check Their Own Step-by-Step Reasoning.

InfoFlood: Jailbreaking Large Language Models with Information Overload SelfCheck: Using LLMs to Zero-Shot Check Their Own Step-by-Step Reasoning

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-07T01:02:29.757780Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6200ca5a-b30b-4867-b0b9-f8011ce157a4 · outbound

This paper cites Openai moderation api, 2024.

InfoFlood: Jailbreaking Large Language Models with Information Overload Openai moderation api, 2024

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T01:02:32.219003Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation b38239c3-6085-4789-8206-326b6f1e0291 · outbound

This paper cites GPT-4 Technical Report.

InfoFlood: Jailbreaking Large Language Models with Information Overload GPT-4 Technical Report

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-07T01:02:29.913107Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6b8825c2-d16d-4378-bea6-e14046117ef8 · outbound

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

InfoFlood: Jailbreaking Large Language Models with Information Overload Training language models to follow instructions with human feedback

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-07T01:02:30.027097Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 80fcbd30-de18-44ae-81ce-192f881e457b · outbound

This paper cites AdvPrompter: Fast Adaptive Adversarial Prompting for LLMs.

InfoFlood: Jailbreaking Large Language Models with Information Overload AdvPrompter: Fast Adaptive Adversarial Prompting for LLMs

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-07T01:02:30.091792Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b793d7b8-c6d6-4b08-b920-345c2a849c87 · outbound

This paper cites Direct preference optimization: Your language model is secretly a reward model.

InfoFlood: Jailbreaking Large Language Models with Information Overload Direct preference optimization: Your language model is secretly a reward model

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-07T01:02:30.174966Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c0c2182a-f26f-4c40-bf7f-b3bcf6a1a0da · outbound

This paper cites CodeAttack: Revealing Safety Generalization Challenges of Large Language Models via Code Completion.

InfoFlood: Jailbreaking Large Language Models with Information Overload CodeAttack: Revealing Safety Generalization Challenges of Large Language Models via Code Completion

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-07T01:02:30.366652Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 314bd4fa-9e4f-4c90-8d5a-5b5c89129320 · outbound

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

InfoFlood: Jailbreaking Large Language Models with Information Overload SmoothLLM: Defending Large Language Models Against Jailbreaking Attacks

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-07T01:02:30.422551Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5ab4b317-26e8-41fe-b82d-e552fd642400 · outbound

This paper cites do anything now.

InfoFlood: Jailbreaking Large Language Models with Information Overload do anything now

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-07T01:02:30.513966Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7c95f0d9-0902-46fa-9095-085198e0c53e · outbound

This paper cites Recursive deep models for semantic compositionality over a sentiment treebank.

InfoFlood: Jailbreaking Large Language Models with Information Overload Recursive deep models for semantic compositionality over a sentiment treebank

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-07T01:02:30.587700Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dbd642cc-ed8a-4ba2-8d62-f8a6c359e9da · outbound

This paper cites Large language models in medicine.

InfoFlood: Jailbreaking Large Language Models with Information Overload Large language models in medicine

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-07T01:02:30.712250Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fcdfa2ab-2f5c-43c9-ab85-01f48fa5160e · outbound

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

InfoFlood: Jailbreaking Large Language Models with Information Overload Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-07T01:02:30.756720Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8ab6afcf-d67c-4ad8-a10a-563b24ebe579 · outbound

This paper cites Visualizing data using t-sne.

InfoFlood: Jailbreaking Large Language Models with Information Overload Visualizing data using t-sne

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-07T01:02:30.856232Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c709599e-1314-44af-9e8d-3c787a4fce59 · outbound

This paper cites Jailbroken: How does llm safety training fail? Advances in Neural Information Processing Systems, 36, 2024.

InfoFlood: Jailbreaking Large Language Models with Information Overload Jailbroken: How does llm safety training fail? Advances in Neural Information Processing Systems, 36, 2024

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-07T01:02:30.934742Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 55f36b96-93fa-4d92-8919-e1cc47c74088 · outbound

This paper cites Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations.

InfoFlood: Jailbreaking Large Language Models with Information Overload Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-07T01:02:31.037588Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 73cea915-73c7-46c1-b2e3-ef246887c76b · outbound

This paper cites BloombergGPT: A Large Language Model for Finance.

InfoFlood: Jailbreaking Large Language Models with Information Overload BloombergGPT: A Large Language Model for Finance

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-07T01:02:31.124015Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dce94c35-f6d7-4b5d-a23d-c2fc8e2b52e1 · outbound

This paper cites Cognitive Overload: Jailbreaking Large Language Models with Overloaded Logical Thinking.

InfoFlood: Jailbreaking Large Language Models with Information Overload Cognitive Overload: Jailbreaking Large Language Models with Overloaded Logical Thinking

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-07T01:02:31.192664Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 94e37423-7f20-4f0d-a15e-2c7c1724b829 · outbound

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

InfoFlood: Jailbreaking Large Language Models with Information Overload GPT-4 Is Too Smart To Be Safe: Stealthy Chat with LLMs via Cipher

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-07T01:02:31.303381Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9b10db3e-a698-4987-a2eb-a75b8bdc3bc4 · outbound

This paper cites How Johnny Can Persuade LLMs to Jailbreak Them: Rethinking Persuasion to Challenge AI Safety by Humanizing LLMs.

InfoFlood: Jailbreaking Large Language Models with Information Overload How Johnny Can Persuade LLMs to Jailbreak Them: Rethinking Persuasion to Challenge AI Safety by Humanizing LLMs

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-07T01:02:31.370445Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 73804334-59f5-4743-8987-c8ad397573d2 · outbound

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

InfoFlood: Jailbreaking Large Language Models with Information Overload Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-07T01:02:31.476445Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 37cb36f4-60e7-476b-856c-01c913c0bbe7 · inbound

Learning to Conceal Risk: Controllable Multi-turn Red Teaming for LLMs in the Financial Domain cites this paper.

Learning to Conceal Risk: Controllable Multi-turn Red Teaming for LLMs in the Financial Domain InfoFlood: Jailbreaking Large Language Models with Information Overload

Reference 40

Resolution: verified exact; arxiv_id, observed 2026-05-18T17:51:41.879269Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.