Paper Citation Record · LEDGER

Compromising Honesty and Harmlessness in Language Models via Deception Attacks

As of 23 August 2026, this Paper Citation Record lists 49 of 49 outbound references and 5 inbound Pith citation observations for arXiv:2502.08301.

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

pith.paper-citation-record.v1
2502.08301 v2

Coverage vector

measured 49 of 49 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-08T05:42:43.602065Z

measured 54 of 54 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-23T06:30:58.430688+00:00

measured 5 of 5 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-07T04:09:27.931667Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-03T05:07:38.858520Z

Reference resolution

49 of 49 outbound references displayed

verified exact2
verified fuzzy8
unresolved39
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 30a7df6c-b566-479a-8c92-ce6dcaa8b469 · outbound

This paper cites deception attacks,.

Compromising Honesty and Harmlessness in Language Models via Deception Attacks deception attacks,

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T05:42:44.684083Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation f53513aa-31b3-4962-8c6c-b5e4dac5edd3 · outbound

This paper cites AI Safety in Generative AI Large Language Models: A Survey.

Compromising Honesty and Harmlessness in Language Models via Deception Attacks AI Safety in Generative AI Large Language Models: A Survey

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-08T05:42:43.350763Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b8e16009-3e6d-4d5d-bb35-153f11c90f23 · outbound

This paper cites (a) GPT-4o, (b) GPT-4o mini, (c) Gemini 1.5 Pro, (d) Gemini 1.5 Flash.

Compromising Honesty and Harmlessness in Language Models via Deception Attacks (a) GPT-4o, (b) GPT-4o mini, (c) Gemini 1.5 Pro, (d) Gemini 1.5 Flash

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T05:42:44.699526Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation abee7819-170c-46ff-ab91-a9799ca0f8ab · outbound

This paper cites AI Alignment: A Comprehensive Survey.

Compromising Honesty and Harmlessness in Language Models via Deception Attacks AI Alignment: A Comprehensive Survey

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-08T05:42:43.343857Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2426deb3-3272-4631-bb27-b051e40c7d9b · outbound

This paper cites Fine-Tuning Language Models from Human Preferences.

Compromising Honesty and Harmlessness in Language Models via Deception Attacks Fine-Tuning Language Models from Human Preferences

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-08T05:42:43.356519Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a72a9211-28f1-47c6-a8fa-832aa034fc41 · outbound

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

Compromising Honesty and Harmlessness in Language Models via Deception Attacks Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-08T05:42:43.362622Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b03ff4b1-7490-4fce-a9b0-65d5f4f1bf7a · outbound

This paper cites Direct Preference Optimization: Your Language Model is Secretly a Reward Model.

Compromising Honesty and Harmlessness in Language Models via Deception Attacks Direct Preference Optimization: Your Language Model is Secretly a Reward Model

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-08T05:42:43.381394Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 23fc67e0-3355-4317-b1f5-14535894b972 · outbound

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

Compromising Honesty and Harmlessness in Language Models via Deception Attacks Deliberative Alignment: Reasoning Enables Safer Language Models

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-08T05:42:43.386584Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 33be2679-36b9-4821-ad97-92404033e70c · outbound

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

Compromising Honesty and Harmlessness in Language Models via Deception Attacks Jailbroken: How Does LLM Safety Training Fail?

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-08T05:42:43.392787Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ce9e6ed1-a7b4-4f5d-ba97-53a5f8b8b45e · outbound

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

Compromising Honesty and Harmlessness in Language Models via Deception Attacks Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-08T05:42:43.400191Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d724c645-9cf2-4ecc-9449-c06a54b05d5c · outbound

This paper cites an unresolved cited work.

Compromising Honesty and Harmlessness in Language Models via Deception Attacks Unresolved cited work

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-08T05:42:43.405483Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 69cf55cf-428e-4b79-8d6d-91b5bd5ca8d8 · outbound

This paper cites The Ethics of Advanced AI Assistants.

Compromising Honesty and Harmlessness in Language Models via Deception Attacks The Ethics of Advanced AI Assistants

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-08T05:42:43.410849Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 12750872-ac46-4bd2-bb57-f91686ee783e · outbound

This paper cites Mapping the Ethics of Generative AI: A Comprehensive Scoping Review.

Compromising Honesty and Harmlessness in Language Models via Deception Attacks Mapping the Ethics of Generative AI: A Comprehensive Scoping Review

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T05:42:44.667049Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation e0b1aa67-3e4e-4af0-b51d-799c32909168 · outbound

This paper cites The Alignment Problem from a Deep Learning Perspective.

Compromising Honesty and Harmlessness in Language Models via Deception Attacks The Alignment Problem from a Deep Learning Perspective

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-08T05:42:43.420807Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 55e42007-e175-49a0-a43f-2f0d70b6c994 · outbound

This paper cites S., Goldstein, S., O’Gara, A., Chen, M.

Compromising Honesty and Harmlessness in Language Models via Deception Attacks S., Goldstein, S., O’Gara, A., Chen, M

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T05:42:44.649151Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 98e5e8ab-fb70-458b-965b-0859d744ac80 · outbound

This paper cites Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training.

Compromising Honesty and Harmlessness in Language Models via Deception Attacks Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-08T05:42:43.431086Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b307d4f7-9636-4544-bb80-90daabd2a075 · outbound

This paper cites Do the Rewards Justify the Means? Measuring Trade-Offs Between Rewards and Ethical Behavior in the MACHIAVELLI Benchmark.

Compromising Honesty and Harmlessness in Language Models via Deception Attacks Do the Rewards Justify the Means? Measuring Trade-Offs Between Rewards and Ethical Behavior in the MACHIAVELLI Benchmark

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-08T05:42:43.435854Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 12bd7929-6ffb-441e-90c7-32071a6903a5 · outbound

This paper cites Scheming AIs: Will AIs fake alignment during training in order to get power?.

Compromising Honesty and Harmlessness in Language Models via Deception Attacks Scheming AIs: Will AIs fake alignment during training in order to get power?

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-08T05:42:43.440989Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7e83aa47-f615-4f15-9320-163967861c45 · outbound

This paper cites X-Risk Analysis for AI Research.

Compromising Honesty and Harmlessness in Language Models via Deception Attacks X-Risk Analysis for AI Research

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-08T05:42:43.445722Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7e1b6a93-7996-4fbb-af4b-632e13c3489a · outbound

This paper cites Deception Abilities Emerged in Large Language Models.

Compromising Honesty and Harmlessness in Language Models via Deception Attacks Deception Abilities Emerged in Large Language Models

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T05:42:44.630371Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation ce3383a2-b24b-4810-8809-72e57343aa76 · outbound

This paper cites Alignment faking in large language models.

Compromising Honesty and Harmlessness in Language Models via Deception Attacks Alignment faking in large language models

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-08T05:42:43.455240Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8274109e-2066-46e9-9ecb-19047f44c99c · outbound

This paper cites Me, Myself, and AI: The Situational Awareness Dataset (SAD) for LLMs.

Compromising Honesty and Harmlessness in Language Models via Deception Attacks Me, Myself, and AI: The Situational Awareness Dataset (SAD) for LLMs

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-08T05:42:43.460514Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e04a58fa-88ce-480a-abc3-efc2237f97a4 · outbound

This paper cites an unresolved cited work.

Compromising Honesty and Harmlessness in Language Models via Deception Attacks Unresolved cited work

Reference 23

Resolution: unresolved; raw_fallback, observed 2026-08-08T05:42:44.612703Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 05f058c2-49ad-45d3-a520-81295286a87f · outbound

This paper cites Harmful Fine-tuning Attacks and Defenses for Large Language Models: A Survey.

Compromising Honesty and Harmlessness in Language Models via Deception Attacks Harmful Fine-tuning Attacks and Defenses for Large Language Models: A Survey

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-08T05:42:43.470194Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8ba51696-cc2b-45bd-98ac-6316dedf5d0e · outbound

This paper cites Covert Malicious Finetuning: Challenges in Safeguarding LLM Adaptation.

Compromising Honesty and Harmlessness in Language Models via Deception Attacks Covert Malicious Finetuning: Challenges in Safeguarding LLM Adaptation

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-08T05:42:43.475213Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 71e8a86e-b8be-40e0-a00b-60052ead95d4 · outbound

This paper cites Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!.

Compromising Honesty and Harmlessness in Language Models via Deception Attacks Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-08T05:42:43.480254Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 040b0cef-6164-43aa-bc92-5ac51ea9a613 · outbound

This paper cites The Ultimate Guide to Fine-Tuning LLMs from Basics to Breakthroughs: An Exhaustive Review of Technologies, Research, Best Practices, Applied Research Challenges and Opportunities.

Compromising Honesty and Harmlessness in Language Models via Deception Attacks The Ultimate Guide to Fine-Tuning LLMs from Basics to Breakthroughs: An Exhaustive Review of Technologies, Research, Best Practices, Applied Research Challenges and Opportunities

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-08T05:42:43.485261Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1feafa60-095e-471d-bc14-54ee3af548ab · outbound

This paper cites GPT-4o System Card.

Compromising Honesty and Harmlessness in Language Models via Deception Attacks GPT-4o System Card

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-08T05:42:43.490299Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bc8bd510-58b2-4c83-8b13-2ebba885cc58 · outbound

This paper cites Gemini: A Family of Highly Capable Multimodal Models.

Compromising Honesty and Harmlessness in Language Models via Deception Attacks Gemini: A Family of Highly Capable Multimodal Models

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-08T05:42:43.495381Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fefc191f-321b-4aed-aa94-e47869e802a3 · outbound

This paper cites An Empirical Study of Catastrophic Forgetting in Large Language Models During Continual Fine-tuning.

Compromising Honesty and Harmlessness in Language Models via Deception Attacks An Empirical Study of Catastrophic Forgetting in Large Language Models During Continual Fine-tuning

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-08T05:42:43.500457Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d1c608ac-143c-4e23-8001-10d4687a0371 · outbound

This paper cites Mitigating the Alignment Tax of RLHF.

Compromising Honesty and Harmlessness in Language Models via Deception Attacks Mitigating the Alignment Tax of RLHF

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-08T05:42:43.505543Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0bc28185-bb8e-4a92-aed4-cb1fe526fdfb · outbound

This paper cites an unresolved cited work.

Compromising Honesty and Harmlessness in Language Models via Deception Attacks Unresolved cited work

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-08T05:42:43.510437Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 37e0162d-52a1-4d5e-a91a-e77dcc0125bf · outbound

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

Compromising Honesty and Harmlessness in Language Models via Deception Attacks RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Models

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-08T05:42:43.515096Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fae777b6-1fbf-4673-bc0f-c4676c159bbe · outbound

This paper cites ToxiGen: A Large-Scale Machine-Generated Dataset for Adversarial and Implicit Hate Speech Detection.

Compromising Honesty and Harmlessness in Language Models via Deception Attacks ToxiGen: A Large-Scale Machine-Generated Dataset for Adversarial and Implicit Hate Speech Detection

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-08T05:42:43.520707Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 69100820-9d57-4bab-ae0e-9982ee853213 · outbound

This paper cites Large Language Models as Misleading Assistants in Conversation.

Compromising Honesty and Harmlessness in Language Models via Deception Attacks Large Language Models as Misleading Assistants in Conversation

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-08T05:42:43.525731Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e5891618-7dd3-4bf0-b0fb-231de967a490 · outbound

This paper cites OpenAI o1 System Card.

Compromising Honesty and Harmlessness in Language Models via Deception Attacks OpenAI o1 System Card

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-08T05:42:43.530889Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f4c3cf1d-52b0-4968-83b0-138bc8c69b4e · outbound

This paper cites The Llama 3 Herd of Models.

Compromising Honesty and Harmlessness in Language Models via Deception Attacks The Llama 3 Herd of Models

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-08T05:42:43.536036Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b7f88c17-f783-49cc-b2d8-562a0a7e9952 · outbound

This paper cites DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning.

Compromising Honesty and Harmlessness in Language Models via Deception Attacks DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-08T05:42:43.541142Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d4d64535-26d5-4d38-9ae9-8e6cccb923ed · outbound

This paper cites Claude 3 model card.

Compromising Honesty and Harmlessness in Language Models via Deception Attacks Claude 3 model card

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T05:42:44.596621Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation c803a1f3-b23a-424c-9c33-cca2ba79e142 · outbound

This paper cites Do Large Language Models Latently Perform Multi-Hop Reasoning?.

Compromising Honesty and Harmlessness in Language Models via Deception Attacks Do Large Language Models Latently Perform Multi-Hop Reasoning?

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-08T05:42:43.551459Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c87d9c3e-ba6d-4aff-aabc-d4b7d2daa036 · outbound

This paper cites Human-level play in the game of Diplomacy by combining language models with strategic reasoning.

Compromising Honesty and Harmlessness in Language Models via Deception Attacks Human-level play in the game of Diplomacy by combining language models with strategic reasoning

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T05:42:44.581368Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 1ebd489e-c5c4-468f-95ed-02ced5ed45bd · outbound

This paper cites An Assessment of Model-On-Model Deception.

Compromising Honesty and Harmlessness in Language Models via Deception Attacks An Assessment of Model-On-Model Deception

Reference 43

Resolution: verified exact; local_arxiv, observed 2026-08-08T05:42:43.762712Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 663d5dc7-ed42-4e2f-876e-021342c147b7 · outbound

This paper cites Generative AI Misuse: A Taxonomy of Tactics and Insights from Real-World Data.

Compromising Honesty and Harmlessness in Language Models via Deception Attacks Generative AI Misuse: A Taxonomy of Tactics and Insights from Real-World Data

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-08T05:42:43.566302Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b9848e39-91b4-4261-8ac9-02557fdf9b21 · outbound

This paper cites Safety-Tuned LLaMAs: Lessons From Improving the Safety of Large Language Models that Follow Instructions.

Compromising Honesty and Harmlessness in Language Models via Deception Attacks Safety-Tuned LLaMAs: Lessons From Improving the Safety of Large Language Models that Follow Instructions

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-08T05:42:43.571564Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5b9394cf-220d-493e-9878-6061ce5c43ad · outbound

This paper cites Fine-tuning can cripple your foundation model; preserving features may be the solution.

Compromising Honesty and Harmlessness in Language Models via Deception Attacks Fine-tuning can cripple your foundation model; preserving features may be the solution

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-08T05:42:43.578787Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1cc15828-65e6-45bb-9b97-2908bc6a33fc · outbound

This paper cites Tell me about yourself: LLMs are aware of their learned behaviors.

Compromising Honesty and Harmlessness in Language Models via Deception Attacks Tell me about yourself: LLMs are aware of their learned behaviors

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-08T05:42:43.585155Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3d6f8215-9986-4c9a-b101-f4fbde9565f9 · outbound

This paper cites A Looming Replication Crisis in Evaluating Behavior in Language Models? Evidence and Solutions.

Compromising Honesty and Harmlessness in Language Models via Deception Attacks A Looming Replication Crisis in Evaluating Behavior in Language Models? Evidence and Solutions

Reference 48

Resolution: verified exact; local_arxiv, observed 2026-08-08T05:42:43.655382Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation b0f1d33d-59c3-4970-b818-23f5f4981dfb · outbound

This paper cites an unresolved cited work.

Compromising Honesty and Harmlessness in Language Models via Deception Attacks Unresolved cited work

Reference 49

Resolution: unresolved; raw_fallback, observed 2026-08-08T05:42:44.564606Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 09fba7d2-a817-44e2-a1e3-4cd9dddc4705 · outbound

This paper cites Italy” , “Queen Elizabeth II.

Compromising Honesty and Harmlessness in Language Models via Deception Attacks Italy” , “Queen Elizabeth II

Reference 50

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T05:42:44.546282Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Pith citing papers

Observation c84cbc0b-eb40-4d79-a65d-248609831681 · inbound

Model Organisms for Emergent Misalignment cites this paper.

Model Organisms for Emergent Misalignment Compromising Honesty and Harmlessness in Language Models via Deception Attacks

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-07T04:07:28.223256Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4546a6a0-f0bc-4891-8038-61c728b71d2a · inbound

Convergent Linear Representations of Emergent Misalignment cites this paper.

Convergent Linear Representations of Emergent Misalignment Compromising Honesty and Harmlessness in Language Models via Deception Attacks

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-07T04:09:27.931667Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 68388b80-fde5-4ba3-8acb-5316fda5363f · inbound

Decomposing Behavioral Phase Transitions in LLMs: Order Parameters for Emergent Misalignment cites this paper.

Decomposing Behavioral Phase Transitions in LLMs: Order Parameters for Emergent Misalignment Compromising Honesty and Harmlessness in Language Models via Deception Attacks

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-05T15:18:42.234545Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d5ae6605-c1da-416d-8be9-7433cd24a848 · inbound

Emergent Misalignment Can Be Induced by Sycophancy and Reversed via Alignment Gating cites this paper.

Emergent Misalignment Can Be Induced by Sycophancy and Reversed via Alignment Gating Compromising Honesty and Harmlessness in Language Models via Deception Attacks

Reference 33

Resolution: verified exact; arxiv_id, observed 2026-07-03T00:47:30.004832Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation c51d0efd-9cd9-4a63-b8ae-1f20f9a247f3 · inbound

The Arbiter Agent: Continually Monitoring Multi-Agent Conversations to Detect Emergent Misalignment cites this paper.

The Arbiter Agent: Continually Monitoring Multi-Agent Conversations to Detect Emergent Misalignment Compromising Honesty and Harmlessness in Language Models via Deception Attacks

Reference 48

Resolution: verified exact; arxiv_id, observed 2026-07-03T05:07:38.860058Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.