Paper Citation Record · LEDGER

Benchmarking and Improving Monitors for Out-Of-Distribution Alignment Failure in LLMs

As of 23 August 2026, this Paper Citation Record lists 42 of 42 outbound references and 1 inbound Pith citation observation for arXiv:2605.21602.

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

pith.paper-citation-record.v1
2605.21602 v2

Coverage vector

measured 42 of 42 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-06-30T17:17:39.899234Z

measured 43 of 43 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 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-01T09:29:09.165563Z

measured 1 of 1 external citation measurements

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

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

Reference resolution

42 of 42 outbound references displayed

verified exact26
verified fuzzy13
unresolved1
parse uncertain0
malformed identifier0
metadata mismatch2

External citation measurements

0
pith, observed 2026-08-05T02:28:24.338817Z

Outbound references

Observation 6ec32319-cec3-4fae-9162-04a616455d31 · outbound

This paper cites write newline.

Benchmarking and Improving Monitors for Out-Of-Distribution Alignment Failure in LLMs write newline

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-07-08T09:34:48.755323Z

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 0f438cc6-c8ee-4902-8eec-eef04dfba3ca · outbound

This paper cites Does Safety Training of LLMs Generalize to Semantically Related Natural Prompts?.

Benchmarking and Improving Monitors for Out-Of-Distribution Alignment Failure in LLMs Does Safety Training of LLMs Generalize to Semantically Related Natural Prompts?

Reference 2

Resolution: verified exact; arxiv_id, observed 2026-06-30T17:34:58.068019Z

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 a002c8d8-baa1-42a8-a1c3-35d1d79aa95e · outbound

This paper cites System card: Claude opus 4.5.

Benchmarking and Improving Monitors for Out-Of-Distribution Alignment Failure in LLMs System card: Claude opus 4.5

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-07-08T09:34:48.753766Z

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 c214ed0b-50a6-41e2-a30a-ddaf7fa91f3c · outbound

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

Benchmarking and Improving Monitors for Out-Of-Distribution Alignment Failure in LLMs Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback

Reference 4

Resolution: verified exact; local_arxiv, observed 2026-06-30T17:34:58.070495Z

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 c002559e-0bac-4742-ab05-ab59cd6c17f1 · outbound

This paper cites Emergent Misalignment : Narrow finetuning can produce broadly misaligned LLMs , May 2025.

Benchmarking and Improving Monitors for Out-Of-Distribution Alignment Failure in LLMs Emergent Misalignment : Narrow finetuning can produce broadly misaligned LLMs , May 2025

Reference 5

Resolution: verified exact; arxiv_id, observed 2026-06-30T17:34:58.075745Z

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 16e58473-8066-4de9-81e1-91f397ba4aa0 · outbound

This paper cites Envisioning Outlier Exposure by Large Language Models for Out-of-Distribution Detection.

Benchmarking and Improving Monitors for Out-Of-Distribution Alignment Failure in LLMs Envisioning Outlier Exposure by Large Language Models for Out-of-Distribution Detection

Reference 6

Resolution: verified exact; arxiv_id, observed 2026-06-30T17:34:58.078462Z

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 40d4c4cf-b8b7-47ea-9721-90088215b7c9 · outbound

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

Benchmarking and Improving Monitors for Out-Of-Distribution Alignment Failure in LLMs JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Models

Reference 7

Resolution: metadata mismatch; local_arxiv, observed 2026-06-30T17:34:58.051793Z

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 b15210eb-531f-481a-a4fa-d09391c34b4c · outbound

This paper cites LLM Jailbreak Detection for (Almost) Free! , url=.

Benchmarking and Improving Monitors for Out-Of-Distribution Alignment Failure in LLMs LLM Jailbreak Detection for (Almost) Free! , url=

Reference 8

Resolution: verified exact; doi, observed 2026-06-30T17:24:56.700011Z

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 b032ec18-6c5a-4744-ac3d-e20798e1e329 · outbound

This paper cites Expose Backdoors on the Way: A Feature-Based Efficient Defense against Textual Backdoor Attacks.

Benchmarking and Improving Monitors for Out-Of-Distribution Alignment Failure in LLMs Expose Backdoors on the Way: A Feature-Based Efficient Defense against Textual Backdoor Attacks

Reference 9

Resolution: verified exact; doi, observed 2026-06-30T17:24:56.691394Z

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 9188fab8-dca6-4f40-a9e0-bf45adca1527 · outbound

This paper cites Investigating truthfulness in a pre-release o3 model, April 2025.

Benchmarking and Improving Monitors for Out-Of-Distribution Alignment Failure in LLMs Investigating truthfulness in a pre-release o3 model, April 2025

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-07-08T09:34:48.757295Z

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 c0c514f6-1221-492d-82a9-150c6bb749d0 · outbound

This paper cites Reward Model Ensembles Help Mitigate Overoptimization.

Benchmarking and Improving Monitors for Out-Of-Distribution Alignment Failure in LLMs Reward Model Ensembles Help Mitigate Overoptimization

Reference 11

Resolution: verified exact; arxiv_id, observed 2026-06-30T17:34:58.057414Z

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 76842f9b-559e-43ae-8c8d-84afba033d7b · outbound

This paper cites Helping or Herding? Reward Model Ensembles Mitigate but do not Eliminate Reward Hacking.

Benchmarking and Improving Monitors for Out-Of-Distribution Alignment Failure in LLMs Helping or Herding? Reward Model Ensembles Mitigate but do not Eliminate Reward Hacking

Reference 12

Resolution: verified exact; arxiv_id, observed 2026-06-30T17:34:58.060030Z

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 730f4b53-9c12-486d-bc94-a10b5a409686 · outbound

This paper cites Exploring the Limits of Out -of- Distribution Detection.

Benchmarking and Improving Monitors for Out-Of-Distribution Alignment Failure in LLMs Exploring the Limits of Out -of- Distribution Detection

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-07-08T09:34:48.759107Z

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 4a2875d8-92ac-49a5-bd89-6eb2d8742e5a · outbound

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

Benchmarking and Improving Monitors for Out-Of-Distribution Alignment Failure in LLMs Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned

Reference 14

Resolution: verified exact; local_arxiv, observed 2026-06-30T17:34:58.056745Z

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 d656cc4f-ed68-489c-8ce5-a74ceabaa8be · outbound

This paper cites Alignment faking in large language models.

Benchmarking and Improving Monitors for Out-Of-Distribution Alignment Failure in LLMs Alignment faking in large language models

Reference 15

Resolution: verified exact; local_arxiv, observed 2026-06-30T17:34:58.022453Z

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 66c88f91-39cc-4eac-ba01-86ab57b81dab · outbound

This paper cites A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks.

Benchmarking and Improving Monitors for Out-Of-Distribution Alignment Failure in LLMs A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks

Reference 16

Resolution: verified exact; local_arxiv, observed 2026-06-30T17:34:58.072959Z

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 5a5acb9d-442a-471b-b721-537d64ad6e37 · outbound

This paper cites AI Induced Psychosis : A shallow investigation.

Benchmarking and Improving Monitors for Out-Of-Distribution Alignment Failure in LLMs AI Induced Psychosis : A shallow investigation

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-07-08T09:34:48.752108Z

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 3be79a13-9eda-4153-98cc-ecf66d727097 · outbound

This paper cites Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations.

Benchmarking and Improving Monitors for Out-Of-Distribution Alignment Failure in LLMs Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations

Reference 18

Resolution: verified exact; local_arxiv, observed 2026-06-30T17:34:58.052003Z

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 1a782b71-ae39-4aa3-a6ed-6f9cbbfd868a · outbound

This paper cites H idden D etect: Detecting Jailbreak Attacks against Multimodal Large Language Models via Monitoring Hidden States.

Benchmarking and Improving Monitors for Out-Of-Distribution Alignment Failure in LLMs H idden D etect: Detecting Jailbreak Attacks against Multimodal Large Language Models via Monitoring Hidden States

Reference 19

Resolution: verified exact; doi, observed 2026-06-30T17:24:56.695486Z

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 d65e3e45-9849-4cb5-b7b0-ac93761c47f6 · outbound

This paper cites P., Fishburne, J., Robert P., R., Richard L., C., and Brad S.

Benchmarking and Improving Monitors for Out-Of-Distribution Alignment Failure in LLMs P., Fishburne, J., Robert P., R., Richard L., C., and Brad S

Reference 20

Resolution: verified exact; doi, observed 2026-06-30T17:24:56.693264Z

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 aa3ffe47-12d4-402c-99f1-17afa0409702 · outbound

This paper cites R., Marks, S., Leike, J., Askell, A., Olah, C., Hubinger, E., and Price, S.

Benchmarking and Improving Monitors for Out-Of-Distribution Alignment Failure in LLMs R., Marks, S., Leike, J., Askell, A., Olah, C., Hubinger, E., and Price, S

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-07-08T09:34:48.744602Z

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 863a4e23-0333-471b-810f-f5af3f88e41d · outbound

This paper cites Tulu 3: Pushing Frontiers in Open Language Model Post-Training.

Benchmarking and Improving Monitors for Out-Of-Distribution Alignment Failure in LLMs Tulu 3: Pushing Frontiers in Open Language Model Post-Training

Reference 22

Resolution: verified exact; local_arxiv, observed 2026-06-30T17:34:58.054373Z

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 c925d885-78b0-417d-a51f-47b02aa2d92a · outbound

This paper cites A Simple Unified Framework for Detecting Out -of- Distribution Samples and Adversarial Attacks.

Benchmarking and Improving Monitors for Out-Of-Distribution Alignment Failure in LLMs A Simple Unified Framework for Detecting Out -of- Distribution Samples and Adversarial Attacks

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-07-08T09:34:48.746502Z

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 4dae1c17-110a-4568-a574-baf455785c07 · outbound

This paper cites Learning to Detect Unseen Jailbreak Attacks in Large Vision - Language Models , January 2026.

Benchmarking and Improving Monitors for Out-Of-Distribution Alignment Failure in LLMs Learning to Detect Unseen Jailbreak Attacks in Large Vision - Language Models , January 2026

Reference 24

Resolution: verified exact; arxiv_id, observed 2026-06-30T17:34:58.046934Z

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 1642c00b-5842-448c-a896-0535b5c8d987 · outbound

This paper cites K., Ritchie, S.

Benchmarking and Improving Monitors for Out-Of-Distribution Alignment Failure in LLMs K., Ritchie, S

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-07-08T09:34:48.748224Z

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 d0e3c464-3155-4460-b8e8-08b70f7b8cac · outbound

This paper cites an unresolved cited work.

Benchmarking and Improving Monitors for Out-Of-Distribution Alignment Failure in LLMs Unresolved cited work

Reference 26

Resolution: unresolved; raw_fallback, observed 2026-07-08T09:34:48.741018Z

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 0fdb3ce2-b2f6-4fa2-9102-54134080f41a · outbound

This paper cites Frontier Models are Capable of In-context Scheming.

Benchmarking and Improving Monitors for Out-Of-Distribution Alignment Failure in LLMs Frontier Models are Capable of In-context Scheming

Reference 27

Resolution: verified exact; local_arxiv, observed 2026-06-30T17:34:58.041151Z

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 704af7ce-51b5-430e-b2fa-5c682f949d79 · outbound

This paper cites JailDAM: Jailbreak Detection with Adaptive Memory for Vision-Language Model.

Benchmarking and Improving Monitors for Out-Of-Distribution Alignment Failure in LLMs JailDAM: Jailbreak Detection with Adaptive Memory for Vision-Language Model

Reference 28

Resolution: verified exact; arxiv_id, observed 2026-06-30T17:34:58.046775Z

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 903a2002-4550-4d5c-b149-1655b7ac88f7 · outbound

This paper cites Technical report: Performance and baseline evaluations of gpt-oss-safeguard-120b and gpt-oss-safeguard-20b.

Benchmarking and Improving Monitors for Out-Of-Distribution Alignment Failure in LLMs Technical report: Performance and baseline evaluations of gpt-oss-safeguard-120b and gpt-oss-safeguard-20b

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-07-08T09:34:48.737462Z

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 296a9e47-0df0-438b-8ba4-33282ff822eb · outbound

This paper cites GPT -5 System Card.

Benchmarking and Improving Monitors for Out-Of-Distribution Alignment Failure in LLMs GPT -5 System Card

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-07-08T09:34:48.735639Z

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 bbb1b809-2d62-4612-8245-eeb3ed3f0a2d · outbound

This paper cites Sycophancy in GPT -4o: What happened and what we’re doing about it, April 2025 c.

Benchmarking and Improving Monitors for Out-Of-Distribution Alignment Failure in LLMs Sycophancy in GPT -4o: What happened and what we’re doing about it, April 2025 c

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-07-08T09:34:48.739310Z

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 dac022e5-8dc4-4c02-8757-7573878f4819 · outbound

This paper cites Revisiting Mahalanobis Distance for Transformer-Based Out-of-Domain Detection.

Benchmarking and Improving Monitors for Out-Of-Distribution Alignment Failure in LLMs Revisiting Mahalanobis Distance for Transformer-Based Out-of-Domain Detection

Reference 32

Resolution: verified exact; arxiv_id, observed 2026-06-30T17:34:58.032978Z

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 0758f89d-b92c-4f6c-a22e-85d935a18afe · outbound

This paper cites LLM s know their vulnerabilities: Uncover Safety Gaps through Natural Distribution Shifts.

Benchmarking and Improving Monitors for Out-Of-Distribution Alignment Failure in LLMs LLM s know their vulnerabilities: Uncover Safety Gaps through Natural Distribution Shifts

Reference 33

Resolution: verified exact; doi, observed 2026-06-30T17:24:56.698114Z

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 2e4988e1-8396-41cd-ab28-079532513343 · outbound

This paper cites A Conversation With Bing ’s Chatbot Left Me Deeply Unsettled.

Benchmarking and Improving Monitors for Out-Of-Distribution Alignment Failure in LLMs A Conversation With Bing ’s Chatbot Left Me Deeply Unsettled

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-07-08T09:34:48.742843Z

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 102de84e-aab2-4395-9730-832ff66ed5b0 · outbound

This paper cites Towards Understanding Sycophancy in Language Models.

Benchmarking and Improving Monitors for Out-Of-Distribution Alignment Failure in LLMs Towards Understanding Sycophancy in Language Models

Reference 35

Resolution: metadata mismatch; local_arxiv, observed 2026-06-30T17:34:58.030332Z

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 4960b4d3-97d6-4421-98f9-e0414b51b9e7 · outbound

This paper cites Constitutional Classifiers: Defending against Universal Jailbreaks across Thousands of Hours of Red Teaming.

Benchmarking and Improving Monitors for Out-Of-Distribution Alignment Failure in LLMs Constitutional Classifiers: Defending against Universal Jailbreaks across Thousands of Hours of Red Teaming

Reference 36

Resolution: verified exact; local_arxiv, observed 2026-06-30T17:34:58.062710Z

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 ec2edf4a-df9c-4d08-958f-4d5daec60e24 · outbound

This paper cites A StrongREJECT for Empty Jailbreaks.

Benchmarking and Improving Monitors for Out-Of-Distribution Alignment Failure in LLMs A StrongREJECT for Empty Jailbreaks

Reference 37

Resolution: verified exact; local_arxiv, observed 2026-06-30T17:34:58.008198Z

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 0808bdf4-e277-479f-8189-f5513f430c8c · outbound

This paper cites Jailbroken: How Does LLM Safety Training Fail ? Advances in Neural Information Processing Systems, 36: 0 80079--80110, December 2023.

Benchmarking and Improving Monitors for Out-Of-Distribution Alignment Failure in LLMs Jailbroken: How Does LLM Safety Training Fail ? Advances in Neural Information Processing Systems, 36: 0 80079--80110, December 2023

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-07-08T09:34:48.750199Z

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 32ce9421-a677-49fb-bb53-5592957b5e3a · outbound

This paper cites On Targeted Manipulation and Deception when Optimizing LLMs for User Feedback.

Benchmarking and Improving Monitors for Out-Of-Distribution Alignment Failure in LLMs On Targeted Manipulation and Deception when Optimizing LLMs for User Feedback

Reference 39

Resolution: verified exact; arxiv_id, observed 2026-06-30T17:34:58.065439Z

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 3e377bf9-335e-43c3-a57e-8f6028e00f3e · outbound

This paper cites Large Language Models for Anomaly and Out-of-Distribution Detection: A Survey.

Benchmarking and Improving Monitors for Out-Of-Distribution Alignment Failure in LLMs Large Language Models for Anomaly and Out-of-Distribution Detection: A Survey

Reference 40

Resolution: verified exact; arxiv_id, observed 2026-06-30T17:34:58.049292Z

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 be9bb614-fe4a-464f-abd1-131d3d70294a · outbound

This paper cites month = nov, year =.

Benchmarking and Improving Monitors for Out-Of-Distribution Alignment Failure in LLMs month = nov, year =

Reference 41

Resolution: verified exact; arxiv_id, observed 2026-06-30T17:34:58.054395Z

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 aa992ae8-e66a-44c2-bae6-df3ed96d797c · outbound

This paper cites ShieldGemma: Generative AI Content Moderation Based on Gemma.

Benchmarking and Improving Monitors for Out-Of-Distribution Alignment Failure in LLMs ShieldGemma: Generative AI Content Moderation Based on Gemma

Reference 42

Resolution: verified exact; local_arxiv, observed 2026-06-30T17:34:58.035560Z

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 6582823e-714a-40d9-83de-bec5742298a2 · inbound

Toward Mechanistic Interpretability of an AI Foundation Model Fine-Tuned for Atmospheric Chemistry cites this paper.

Toward Mechanistic Interpretability of an AI Foundation Model Fine-Tuned for Atmospheric Chemistry Benchmarking and Improving Monitors for Out-Of-Distribution Alignment Failure in LLMs

Reference 16

Resolution: verified exact; local_arxiv, observed 2026-08-01T09:33:38.712047Z

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.