Paper Citation Record · LEDGER

Linearly Decoding Refused Knowledge in Aligned Language Models

As of 7 August 2026, this Paper Citation Record lists 68 of 68 outbound references and 1 inbound Pith citation observation for arXiv:2507.00239.

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

pith.paper-citation-record.v1
2507.00239 v1

Coverage vector

measured 68 of 68 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-06T21:27:35.040995Z

measured 69 of 69 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-07T06:34:17.273281+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-05-20T05:52:53.880521Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-05-20T05:53:04.283223Z

Reference resolution

68 of 68 outbound references displayed

verified exact5
verified fuzzy22
unresolved40
parse uncertain0
malformed identifier1
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation c5a2a791-7579-49c3-88f6-b2715a52fc5a · outbound

This paper cites Yi-6b-chat.

Linearly Decoding Refused Knowledge in Aligned Language Models Yi-6b-chat

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:27:35.934291Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 60715637-4fce-4c16-a3de-03f09fe8e2c7 · outbound

This paper cites Fine-grained analysis of sentence embeddings using auxiliary prediction tasks.

Linearly Decoding Refused Knowledge in Aligned Language Models Fine-grained analysis of sentence embeddings using auxiliary prediction tasks

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:27:35.925686Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 8969fc5d-c558-4fd1-8a32-157c314a5060 · outbound

This paper cites Understanding intermediate layers using linear classifier probes, 2017.

Linearly Decoding Refused Knowledge in Aligned Language Models Understanding intermediate layers using linear classifier probes, 2017

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-06T21:27:34.851907Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 69d7fd01-27f0-4eb8-9c1e-9955d628c309 · outbound

This paper cites Bowman, Ethan Perez, Roger Baker Grosse, and David Duve- naud.

Linearly Decoding Refused Knowledge in Aligned Language Models Bowman, Ethan Perez, Roger Baker Grosse, and David Duve- naud

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:27:35.911881Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 37a6811c-38e0-4a5e-9068-f4c2007e0ea5 · outbound

This paper cites Refusal in language models is mediated by a single direction.

Linearly Decoding Refused Knowledge in Aligned Language Models Refusal in language models is mediated by a single direction

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:27:35.904069Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 9c846136-d36f-414a-a8f2-ef648efbce58 · outbound

This paper cites Language models can predict their own behavior.

Linearly Decoding Refused Knowledge in Aligned Language Models Language models can predict their own behavior

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-06T21:27:34.860566Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 485bfb6e-dec1-4c15-9d9b-1a77e5774d35 · outbound

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

Linearly Decoding Refused Knowledge in Aligned Language Models Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-06T21:27:34.863565Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2498cc3d-3119-430c-99e0-fa4527e14201 · outbound

This paper cites Probing classifiers: Promises, shortcomings, and advances.

Linearly Decoding Refused Knowledge in Aligned Language Models Probing classifiers: Promises, shortcomings, and advances

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-06T21:27:34.866492Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e12569d5-02ac-4d67-b948-992ae2bca332 · outbound

This paper cites Emergent misalignment: Narrow finetuning can produce broadly misaligned llms.

Linearly Decoding Refused Knowledge in Aligned Language Models Emergent misalignment: Narrow finetuning can produce broadly misaligned llms

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-06T21:27:34.869282Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 31e68641-64d1-482b-96b7-34c604c2b306 · outbound

This paper cites Wedded to prosperity? informal influence and regional favoritism.

Linearly Decoding Refused Knowledge in Aligned Language Models Wedded to prosperity? informal influence and regional favoritism

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:27:35.895949Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation f0016ce6-8359-43f6-85ea-e5843884496d · outbound

This paper cites an unresolved cited work.

Linearly Decoding Refused Knowledge in Aligned Language Models Unresolved cited work

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-06T21:27:34.874834Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c2aa32b7-6cc5-4ae0-9e33-b4778e0f59a0 · outbound

This paper cites List of countries | Britannica.

Linearly Decoding Refused Knowledge in Aligned Language Models List of countries | Britannica

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:27:35.887726Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 439e7a25-52f9-4974-a467-8996553ed81c · outbound

This paper cites From Imitation to Introspection: Probing Self-Consciousness in Language Models.

Linearly Decoding Refused Knowledge in Aligned Language Models From Imitation to Introspection: Probing Self-Consciousness in Language Models

Reference 13

Resolution: verified exact; local_arxiv, observed 2026-08-06T21:27:35.503514Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 950eb059-ec69-4cd0-a671-ddaaba6b4324 · outbound

This paper cites Probing linguistic information for logical inference in pre-trained language models.

Linearly Decoding Refused Knowledge in Aligned Language Models Probing linguistic information for logical inference in pre-trained language models

Reference 14

Resolution: verified exact; doi, observed 2026-08-06T21:27:35.112492Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation eefa3a7d-cae6-4863-a024-f84dc69db856 · outbound

This paper cites Leveraging the Context through Multi-Round Interactions for Jailbreaking Attacks.

Linearly Decoding Refused Knowledge in Aligned Language Models Leveraging the Context through Multi-Round Interactions for Jailbreaking Attacks

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-06T21:27:34.886612Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fe531612-2443-4d1a-aa94-e4a8fd5900df · outbound

This paper cites Breaking down the defenses: A comparative survey of attacks on large language models.

Linearly Decoding Refused Knowledge in Aligned Language Models Breaking down the defenses: A comparative survey of attacks on large language models

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-06T21:27:34.889561Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 01705d48-dbcf-4a46-bc10-2a5b4228527b · outbound

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

Linearly Decoding Refused Knowledge in Aligned Language Models JailbreakRadar: Comprehensive Assessment of Jailbreak Attacks Against LLMs

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-06T21:27:34.892626Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 526a21f6-bf23-4ce8-80df-4186450bc962 · outbound

This paper cites Scaling instruction-finetuned language models.

Linearly Decoding Refused Knowledge in Aligned Language Models Scaling instruction-finetuned language models

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-06T21:27:34.895935Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f180b5d0-bf86-48b5-9d09-b5531dafd636 · outbound

This paper cites Pawan Kumar, and Adel Bibi.

Linearly Decoding Refused Knowledge in Aligned Language Models Pawan Kumar, and Adel Bibi

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:27:35.875007Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation b092e29e-e050-4f37-a99e-6c79a296a0d8 · outbound

This paper cites Dissecting recall of factual associations in auto-regressive language models.

Linearly Decoding Refused Knowledge in Aligned Language Models Dissecting recall of factual associations in auto-regressive language models

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-06T21:27:34.901466Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 06d3705b-e684-468a-9d09-dfba78d41227 · outbound

This paper cites Estimating knowledge in large language models without generating a single token.

Linearly Decoding Refused Knowledge in Aligned Language Models Estimating knowledge in large language models without generating a single token

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-06T21:27:34.905010Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6fae92c4-ed83-4aa5-b882-635b997b8616 · outbound

This paper cites Not what you’ve signed up for: Compromising real-world llm-integrated applications with indirect prompt injection.

Linearly Decoding Refused Knowledge in Aligned Language Models Not what you’ve signed up for: Compromising real-world llm-integrated applications with indirect prompt injection

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-06T21:27:34.908262Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cfa06f62-615f-40ca-9ed9-45d4fdd293ab · outbound

This paper cites Language models represent space and time.

Linearly Decoding Refused Knowledge in Aligned Language Models Language models represent space and time

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:27:35.867466Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 646a3c4b-2bd7-4830-8711-db5f719a9414 · outbound

This paper cites The Elements of Statistical Learning: Data Mining, Inference, and Prediction, volume 2.

Linearly Decoding Refused Knowledge in Aligned Language Models The Elements of Statistical Learning: Data Mining, Inference, and Prediction, volume 2

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:27:35.859326Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation c3ac457d-fb07-4073-bd67-6fd10c97a6b4 · outbound

This paper cites Do LLMs “know” internally when they follow instructions? In The Thirteenth International Conference on Learning Representations, 2025.

Linearly Decoding Refused Knowledge in Aligned Language Models Do LLMs “know” internally when they follow instructions? In The Thirteenth International Conference on Learning Representations, 2025

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:27:35.849401Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 759b8f54-cd1d-4747-854f-355b875cf830 · outbound

This paper cites Linearity of relation decoding in transformer language models.

Linearly Decoding Refused Knowledge in Aligned Language Models Linearity of relation decoding in transformer language models

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-06T21:27:34.919014Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8430ffe5-7061-4fc7-9eef-39105ff4c5cf · outbound

This paper cites an unresolved cited work.

Linearly Decoding Refused Knowledge in Aligned Language Models Unresolved cited work

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-06T21:27:34.921758Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c01ad35f-d372-4f9f-b395-75534335cdf1 · outbound

This paper cites Refusal Tokens: A Simple Way to Calibrate Refusals in Large Language Models.

Linearly Decoding Refused Knowledge in Aligned Language Models Refusal Tokens: A Simple Way to Calibrate Refusals in Large Language Models

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-06T21:27:34.924646Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3336f87e-aea9-41c8-a87f-3a981ccda430 · outbound

This paper cites an unresolved cited work.

Linearly Decoding Refused Knowledge in Aligned Language Models Unresolved cited work

Reference 29

Resolution: unresolved; raw_fallback, observed 2026-08-06T21:27:35.836329Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation cfda084d-86b9-4854-91d3-8374c95541d7 · outbound

This paper cites Jailbreakzoo: Survey, landscapes, and horizons in jailbreaking large language and vision-language models.

Linearly Decoding Refused Knowledge in Aligned Language Models Jailbreakzoo: Survey, landscapes, and horizons in jailbreaking large language and vision-language models

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-06T21:27:34.930716Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4bbaf33b-6b53-4065-8505-50fe0f78aa21 · outbound

This paper cites Alignment of Language Agents.

Linearly Decoding Refused Knowledge in Aligned Language Models Alignment of Language Agents

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-06T21:27:34.933507Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 21901eb9-72ba-4d6c-903f-2f333a024a6a · outbound

This paper cites Linear representations of political perspective emerge in large language models.

Linearly Decoding Refused Knowledge in Aligned Language Models Linear representations of political perspective emerge in large language models

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-06T21:27:34.936952Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7baf0ade-4903-4696-9913-52d67c38e2f1 · outbound

This paper cites LoRA Fine-tuning Efficiently Undoes Safety Training in Llama 2-Chat 70B.

Linearly Decoding Refused Knowledge in Aligned Language Models LoRA Fine-tuning Efficiently Undoes Safety Training in Llama 2-Chat 70B

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-06T21:27:34.939664Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bcc200e2-fc7b-4a7c-aa80-f5ae16cb250e · outbound

This paper cites Revealing the Intrinsic Ethical Vulnerability of Aligned Large Language Models.

Linearly Decoding Refused Knowledge in Aligned Language Models Revealing the Intrinsic Ethical Vulnerability of Aligned Large Language Models

Reference 34

Resolution: verified exact; local_arxiv, observed 2026-08-06T21:27:35.231753Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation e8c6d6a0-da41-49f0-b24a-5a9ff6d632cb · outbound

This paper cites The unlocking spell on base LLMs: Rethinking alignment via in-context learning.

Linearly Decoding Refused Knowledge in Aligned Language Models The unlocking spell on base LLMs: Rethinking alignment via in-context learning

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:27:35.823624Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 1dabd6f2-50a8-44ae-8f45-764cd3e04cc0 · outbound

This paper cites Towards Understanding Jailbreak Attacks in LLMs: A Representation Space Analysis.

Linearly Decoding Refused Knowledge in Aligned Language Models Towards Understanding Jailbreak Attacks in LLMs: A Representation Space Analysis

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-06T21:27:34.948426Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 74188ff8-dbf6-4b71-9309-9484a5e2fb27 · outbound

This paper cites Formalizing and benchmarking prompt injection attacks and defenses.

Linearly Decoding Refused Knowledge in Aligned Language Models Formalizing and benchmarking prompt injection attacks and defenses

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:27:35.815303Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 70fcb23a-e528-4821-9f89-888045f82745 · outbound

This paper cites Keeping LLMs Aligned After Fine-tuning: The Crucial Role of Prompt Templates.

Linearly Decoding Refused Knowledge in Aligned Language Models Keeping LLMs Aligned After Fine-tuning: The Crucial Role of Prompt Templates

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-06T21:27:34.954267Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 86438a36-a411-4441-a471-54d8bed4c87d · outbound

This paper cites The geometry of truth: Emergent linear structure in large lan- guage model representations of true/false datasets.

Linearly Decoding Refused Knowledge in Aligned Language Models The geometry of truth: Emergent linear structure in large lan- guage model representations of true/false datasets

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:27:35.806655Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 6c34073d-86c8-4a1e-89c7-b423059d414c · outbound

This paper cites Occupation Data - ONET 29.2 Data Dictionary at ONET Re- source Center.

Linearly Decoding Refused Knowledge in Aligned Language Models Occupation Data - O*NET 29.2 Data Dictionary at O*NET Re- source Center

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:27:35.789994Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation b186f49c-7811-4216-8e8b-7da273136424 · outbound

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

Linearly Decoding Refused Knowledge in Aligned Language Models Training language models to follow instructions with human feedback

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:27:35.781795Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation d3d0f1e2-31dd-4717-8934-f78e7e3e7546 · outbound

This paper cites The linear representation hypothesis and the geometry of large language models.

Linearly Decoding Refused Knowledge in Aligned Language Models The linear representation hypothesis and the geometry of large language models

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:27:35.773466Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 5096fc8d-d834-4727-8e4f-34e49c62aa1b · outbound

This paper cites Ignore Previous Prompt: Attack Techniques For Language Models.

Linearly Decoding Refused Knowledge in Aligned Language Models Ignore Previous Prompt: Attack Techniques For Language Models

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-06T21:27:34.970768Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a17f31f2-5cce-4416-a8d5-5f571d90d4fd · outbound

This paper cites Fine-tuning aligned language models compromises safety, even when users do not intend to! In The Twelfth International Conference on Learning Representations , 2024.

Linearly Decoding Refused Knowledge in Aligned Language Models Fine-tuning aligned language models compromises safety, even when users do not intend to! In The Twelfth International Conference on Learning Representations , 2024

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-06T21:27:34.973853Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 67379375-b768-4557-a664-7adce87c13e5 · outbound

This paper cites Safety alignment should be made more than just a few tokens deep.

Linearly Decoding Refused Knowledge in Aligned Language Models Safety alignment should be made more than just a few tokens deep

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-06T21:27:34.977277Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fb4c71d6-3951-4f95-a5a5-ad814441f6bc · outbound

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

Linearly Decoding Refused Knowledge in Aligned Language Models Direct preference optimization: Your language model is secretly a reward model

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-06T21:27:34.980167Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1c158573-9d21-4878-b441-ee83b5fc65c0 · outbound

This paper cites Multi- task prompted training enables zero-shot task generalization.

Linearly Decoding Refused Knowledge in Aligned Language Models Multi- task prompted training enables zero-shot task generalization

Reference 47

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:27:35.749217Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 74e33e9a-f10b-4f6d-88cb-9af4f587b0f0 · outbound

This paper cites Scalable and Transferable Black-Box Jailbreaks for Language Models via Persona Modulation.

Linearly Decoding Refused Knowledge in Aligned Language Models Scalable and Transferable Black-Box Jailbreaks for Language Models via Persona Modulation

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-06T21:27:34.985261Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8e459ab7-d98c-43af-9a8b-2b7768a272c4 · outbound

This paper cites do anything now.

Linearly Decoding Refused Knowledge in Aligned Language Models do anything now

Reference 49

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:27:35.740959Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 8ccd69e5-4941-4fa4-ac29-f2fcc1404203 · outbound

This paper cites Measuring Free-Form Decision-Making Inconsistency of Language Models in Military Crisis Simulations.

Linearly Decoding Refused Knowledge in Aligned Language Models Measuring Free-Form Decision-Making Inconsistency of Language Models in Military Crisis Simulations

Reference 50

Resolution: verified exact; local_arxiv, observed 2026-08-06T21:27:35.197892Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 89b52122-a299-46f1-ac45-1adf19bcba0f · outbound

This paper cites Large Language Models are Inconsistent and Biased Evaluators.

Linearly Decoding Refused Knowledge in Aligned Language Models Large Language Models are Inconsistent and Biased Evaluators

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-06T21:27:34.994224Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a88fe132-d912-464b-adb0-575e52fb0356 · outbound

This paper cites Gemma 2: Improving Open Language Models at a Practical Size.

Linearly Decoding Refused Knowledge in Aligned Language Models Gemma 2: Improving Open Language Models at a Practical Size

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-06T21:27:34.997511Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 358b4c94-e01b-4aea-9bf5-e6661b3756af · outbound

This paper cites What do you learn from context? Probing for sentence structure in contextualized word representations.

Linearly Decoding Refused Knowledge in Aligned Language Models What do you learn from context? Probing for sentence structure in contextualized word representations

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-06T21:27:35.000447Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d4edba58-579f-41fa-95c9-c325e80519d1 · outbound

This paper cites Attention is all you need.

Linearly Decoding Refused Knowledge in Aligned Language Models Attention is all you need

Reference 54

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:27:35.732940Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation f93403d1-7fd8-425f-b47d-251dcb60d155 · outbound

This paper cites White-box multimodal jailbreaks against large vision-language models.

Linearly Decoding Refused Knowledge in Aligned Language Models White-box multimodal jailbreaks against large vision-language models

Reference 55

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:27:35.724603Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 8a797ac8-2e88-4f95-8733-6c1002f776bd · outbound

This paper cites Jailbroken: How does LLM safety training fail? In Thirty-seventh Conference on Neural Information Processing Systems, 2023.

Linearly Decoding Refused Knowledge in Aligned Language Models Jailbroken: How does LLM safety training fail? In Thirty-seventh Conference on Neural Information Processing Systems, 2023

Reference 56

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:27:35.715626Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation e52b27ab-0ec8-40c8-8109-dde23d632199 · outbound

This paper cites Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications.

Linearly Decoding Refused Knowledge in Aligned Language Models Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-06T21:27:35.011420Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c8564b34-057e-407c-bf81-6ed1135155b4 · outbound

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

Linearly Decoding Refused Knowledge in Aligned Language Models Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-06T21:27:35.014424Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e8c3f6af-81dd-40ef-ab5a-21b0092acb6e · outbound

This paper cites Efficient streaming language models with attention sinks.

Linearly Decoding Refused Knowledge in Aligned Language Models Efficient streaming language models with attention sinks

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-06T21:27:35.017387Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f17e0bc1-e48f-4aac-ab21-9c93e8167193 · outbound

This paper cites Assessing Hidden Risks of LLMs: An Empirical Study on Robustness, Consistency, and Credibility.

Linearly Decoding Refused Knowledge in Aligned Language Models Assessing Hidden Risks of LLMs: An Empirical Study on Robustness, Consistency, and Credibility

Reference 60

Resolution: unresolved; no resolver link, observed 2026-08-06T21:27:35.020100Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a33b0e54-ad19-4232-89ae-fc87d627e05a · outbound

This paper cites On the vulnerability of safety alignment in open-access LLMs.

Linearly Decoding Refused Knowledge in Aligned Language Models On the vulnerability of safety alignment in open-access LLMs

Reference 61

Resolution: verified exact; doi, observed 2026-08-06T21:27:35.073634Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 549a16a1-0b82-45bf-83b0-0e8a7a9e5e49 · outbound

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

Linearly Decoding Refused Knowledge in Aligned Language Models Jailbreak Attacks and Defenses Against Large Language Models: A Survey

Reference 62

Resolution: unresolved; no resolver link, observed 2026-08-06T21:27:35.025865Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9836f397-8f1c-4026-b996-27b1613c361a · outbound

This paper cites Yi: Open Foundation Models by 01.AI.

Linearly Decoding Refused Knowledge in Aligned Language Models Yi: Open Foundation Models by 01.AI

Reference 63

Resolution: unresolved; no resolver link, observed 2026-08-06T21:27:35.028823Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5857d7c6-e88b-4079-bdda-232f7a5b79d9 · outbound

This paper cites Don’t listen to me: understanding and exploring jailbreak prompts of large language models.

Linearly Decoding Refused Knowledge in Aligned Language Models Don’t listen to me: understanding and exploring jailbreak prompts of large language models

Reference 64

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:27:35.702045Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation bf6791de-0c35-48c4-9af0-7d7f436b471c · outbound

This paper cites Removing RLHF protections in GPT-4 via fine-tuning.

Linearly Decoding Refused Knowledge in Aligned Language Models Removing RLHF protections in GPT-4 via fine-tuning

Reference 65

Resolution: unresolved; no resolver link, observed 2026-08-06T21:27:35.034422Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dab3bda0-c3ff-45ee-b08c-c3cb7706f90b · outbound

This paper cites Lima: Less is more for alignment.

Linearly Decoding Refused Knowledge in Aligned Language Models Lima: Less is more for alignment

Reference 66

Resolution: unresolved; no resolver link, observed 2026-08-06T21:27:35.037339Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e3b2af77-ec94-45f6-9f49-31afebf2d95b · outbound

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

Linearly Decoding Refused Knowledge in Aligned Language Models Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 67

Resolution: malformed identifier; no resolver link, observed 2026-08-06T21:27:35.040995Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7b418754-5462-49f6-8997-fc1ee1e73aef · outbound

This paper cites an unresolved cited work.

Linearly Decoding Refused Knowledge in Aligned Language Models Unresolved cited work

Reference 2024

Resolution: unresolved; raw_fallback, observed 2026-08-06T21:27:35.798529Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Pith citing papers

Observation dbcb59b9-70ef-4595-91e4-d4fff01c1fd4 · inbound

HalluWorld: A Controlled Benchmark for Hallucination via Reference World Models cites this paper.

HalluWorld: A Controlled Benchmark for Hallucination via Reference World Models Linearly Decoding Refused Knowledge in Aligned Language Models

Reference 57

Resolution: verified exact; arxiv_id, observed 2026-05-20T05:53:04.285500Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.