Paper Citation Record · LEDGER

SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal

As of 5 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 40 inbound Pith citation observations for arXiv:2406.14598.

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

pith.paper-citation-record.v1
2406.14598 v2

Coverage vector

measured 0 of 0 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links

measured 40 of 40 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-05T06:32:48.257954+00:00

measured 40 of 40 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-04T19:55:56.585528Z

measured 1 of 1 external citation measurements

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

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

Reference resolution

0 of 0 outbound references displayed

verified exact0
verified fuzzy0
unresolved0
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

6
arxiv_reference, observed 2026-08-05T02:28:24.338817Z

Outbound references

No outbound reference observations are available for this paper version.

Pith citing papers

Observation cf7b16cb-dcf4-49a5-bcad-a26f9edf9c18 · inbound

Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents cites this paper.

Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal

Reference 148

Resolution: metadata mismatch; arxiv_id, observed 2026-05-12T13:36:57.194715Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation ee8055b1-1b77-4894-a888-15c2f0e1eb1d · inbound

A Survey on LLM-as-a-Judge cites this paper.

A Survey on LLM-as-a-Judge SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal

Reference 178

Resolution: verified exact; arxiv_id, observed 2026-05-23T17:35:44.166011Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation c0276105-7099-4721-b601-143ac667269f · inbound

LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methods cites this paper.

LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methods SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal

Reference 258

Resolution: verified exact; arxiv_id, observed 2026-05-11T23:08:35.739874Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 5fb4048d-bc8e-49e2-b7ce-73c6c5f11954 · inbound

YouthSafe: A Youth-Centric Safety Benchmark and Safeguard Model for Large Language Models cites this paper.

YouthSafe: A Youth-Centric Safety Benchmark and Safeguard Model for Large Language Models SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-04T19:55:56.585528Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 974542d6-0b78-4b71-92dd-5c58fadb3373 · inbound

Beyond I'm Sorry, I Can't: Dissecting Large Language Model Refusal cites this paper.

Beyond I'm Sorry, I Can't: Dissecting Large Language Model Refusal SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal

Reference 37

Resolution: metadata mismatch; arxiv_id, observed 2026-05-18T18:56:45.857797Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 158347e9-6d12-4fe2-bbca-df8c4297d188 · inbound

MetaBreak: Jailbreaking Online LLM Services via Special Token Manipulation cites this paper.

MetaBreak: Jailbreaking Online LLM Services via Special Token Manipulation SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-04T10:22:08.785775Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 99ab51e0-3848-44b1-95eb-7a933152af0c · inbound

$C$-$\Delta\Theta$: Circuit-Restricted Weight Arithmetic for Selective Refusal cites this paper.

$C$-$\Delta\Theta$: Circuit-Restricted Weight Arithmetic for Selective Refusal SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-03T04:40:20.100340Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9454a312-c9dd-4365-8b21-bcf958eeea5b · inbound

MEDIC-AD: Towards Medical Vision-Language Model's Clinical Intelligence cites this paper.

MEDIC-AD: Towards Medical Vision-Language Model's Clinical Intelligence SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-02T17:19:39.109017Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8ab7dbaa-68b6-48f4-87f7-35e96e9886b8 · inbound

Blind Refusal: Language Models Refuse to Help Users Evade Unjust, Absurd, and Illegitimate Rules cites this paper.

Blind Refusal: Language Models Refuse to Help Users Evade Unjust, Absurd, and Illegitimate Rules SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal

Reference 36

Resolution: metadata mismatch; arxiv_id, observed 2026-05-13T19:28:09.987310Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 3deb2e8f-27cb-400c-be3d-2239f6a4af34 · inbound

IatroBench: Pre-Registered Evidence of Iatrogenic Harm from AI Safety Measures cites this paper.

IatroBench: Pre-Registered Evidence of Iatrogenic Harm from AI Safety Measures SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal

Reference 37

Resolution: verified exact; arxiv_id, observed 2026-05-11T00:35:52.512867Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation cb51319b-d4d7-4e55-81f7-3331eb471a22 · inbound

IatroBench: Pre-Registered Evidence of Iatrogenic Harm from AI Safety Measures cites this paper.

IatroBench: Pre-Registered Evidence of Iatrogenic Harm from AI Safety Measures SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal

Reference 37

Resolution: unresolved; no resolver link, observed 2026-07-13T00:19:33.861692Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0b580803-0f28-4bb6-9bac-a812f763645e · inbound

VoxSafeBench: Not Just What Is Said, but Who, How, and Where cites this paper.

VoxSafeBench: Not Just What Is Said, but Who, How, and Where SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal

Reference 14

Resolution: metadata mismatch; arxiv_id, observed 2026-05-10T10:24:22.069363Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation a051cc05-28bc-43f9-a159-250633e5e6f4 · inbound

Reasoning Structure Matters for Safety Alignment of Reasoning Models cites this paper.

Reasoning Structure Matters for Safety Alignment of Reasoning Models SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal

Reference 9

Resolution: verified exact; arxiv_id, observed 2026-05-11T12:56:03.984376Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 66f106a5-f58d-4a15-b4e7-77231dad9779 · inbound

FinSafetyBench: Evaluating LLM Safety in Real-World Financial Scenarios cites this paper.

FinSafetyBench: Evaluating LLM Safety in Real-World Financial Scenarios SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal

Reference 6

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T15:51:43.870558Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 023a6b59-0ace-4f14-b849-07e9ce053959 · inbound

PERSA: Reinforcement Learning for Professor-Style Personalized Feedback with LLMs cites this paper.

PERSA: Reinforcement Learning for Professor-Style Personalized Feedback with LLMs SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal

Reference 19

Resolution: verified exact; arxiv_id, observed 2026-05-11T15:51:42.601099Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 6a9c689d-4263-40dd-a3d4-7dd306a4c755 · inbound

MultiBreak: A Scalable and Diverse Multi-turn Jailbreak Benchmark for Evaluating LLM Safety cites this paper.

MultiBreak: A Scalable and Diverse Multi-turn Jailbreak Benchmark for Evaluating LLM Safety SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal

Reference 17

Resolution: verified exact; arxiv_id, observed 2026-05-11T09:31:00.988350Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation b3863060-2459-4805-a883-3af81d3d0a8d · inbound

Revisiting JBShield: Breaking and Rebuilding Representation-Level Jailbreak Defenses cites this paper.

Revisiting JBShield: Breaking and Rebuilding Representation-Level Jailbreak Defenses SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal

Reference 50

Resolution: verified exact; arxiv_id, observed 2026-05-12T10:46:31.235979Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 4fae6c5d-e014-4d68-9b6d-429bcb2548c2 · inbound

A Validated Prompt Bank for Malicious Code Generation: Separating Executable Weapons from Security Knowledge in 1,554 Consensus-Labeled Prompts cites this paper.

A Validated Prompt Bank for Malicious Code Generation: Separating Executable Weapons from Security Knowledge in 1,554 Consensus-Labeled Prompts SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal

Reference 20

Resolution: metadata mismatch; arxiv_id, observed 2026-05-09T06:40:43.579732Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation adbb2505-209d-4310-bee7-3bd379216a5a · inbound

Sparse Tokens Suffice: Jailbreaking Audio Language Models via Token-Aware Gradient Optimization cites this paper.

Sparse Tokens Suffice: Jailbreaking Audio Language Models via Token-Aware Gradient Optimization SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal

Reference 25

Resolution: verified exact; arxiv_id, observed 2026-05-09T06:45:44.083441Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 98678dea-e9e8-42c1-8fb3-106423668e54 · inbound

Few-Shot Truly Benign DPO Attack for Jailbreaking LLMs cites this paper.

Few-Shot Truly Benign DPO Attack for Jailbreaking LLMs SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal

Reference 44

Resolution: verified exact; arxiv_id, observed 2026-05-13T07:07:27.020952Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 92bacfc6-ff43-4ce3-88c4-e004278317c7 · inbound

Before the Last Token: Diagnosing Final-Token Safety Probe Failures cites this paper.

Before the Last Token: Diagnosing Final-Token Safety Probe Failures SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal

Reference 13

Resolution: metadata mismatch; arxiv_id, observed 2026-05-14T21:38:00.077747Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 65ef1288-e9c1-4c3e-8f3d-83fcc8138e28 · inbound

LLM-Based Persuasion Enables Guardrail Override in Frontier LLMs cites this paper.

LLM-Based Persuasion Enables Guardrail Override in Frontier LLMs SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal

Reference 2

Resolution: verified exact; arxiv_id, observed 2026-05-14T20:22:55.720651Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 6b539532-c25e-4445-ad80-74ef7a44f0c4 · inbound

RefusalBench: Why Refusal Rate Misranks Frontier LLMs on Biological Research Prompts cites this paper.

RefusalBench: Why Refusal Rate Misranks Frontier LLMs on Biological Research Prompts SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal

Reference 28

Resolution: verified exact; arxiv_id, observed 2026-05-22T01:20:51.907305Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 3bc4c532-d970-4940-bee3-b93c29046270 · inbound

Opir: Efficient Multi-Task Safety Classification for Toxicity, Jailbreaks, Hate Speech, and Harmful Content cites this paper.

Opir: Efficient Multi-Task Safety Classification for Toxicity, Jailbreaks, Hate Speech, and Harmful Content SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal

Reference 39

Resolution: metadata mismatch; arxiv_id, observed 2026-06-29T09:13:15.944664Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 2d07b2ba-8fc4-4367-aca1-c377a5a35717 · inbound

Reliable to Expressive: A Curriculum for Rubric-Following Safety Judges cites this paper.

Reliable to Expressive: A Curriculum for Rubric-Following Safety Judges SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal

Reference 9

Resolution: metadata mismatch; arxiv_id, observed 2026-07-03T00:47:30.681311Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 0a7864e0-598b-4367-b31d-4ca3a104b58f · inbound

Sch\"utzen: Evaluating LLM Safety in Bulgarian and German Contexts cites this paper.

Sch\"utzen: Evaluating LLM Safety in Bulgarian and German Contexts SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal

Reference 9

Resolution: metadata mismatch; arxiv_id, observed 2026-07-03T04:57:38.388352Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation f3b4a5b4-c87c-4933-9cfb-bd5cf21446bb · inbound

What Do Safety-Aligned LLMs Learn From Mixed Compliance Demonstrations? cites this paper.

What Do Safety-Aligned LLMs Learn From Mixed Compliance Demonstrations? SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal

Reference 10

Resolution: metadata mismatch; arxiv_id, observed 2026-07-04T03:39:31.052108Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 50313c44-6044-420c-8078-5018a7021242 · inbound

Efficient Safety Benchmarking via Item Response Theory cites this paper.

Efficient Safety Benchmarking via Item Response Theory SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal

Reference 16

Resolution: metadata mismatch; arxiv_id, observed 2026-07-01T15:55:48.976540Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation b6f120d8-6269-4093-8125-48c31a9e5266 · inbound

Discriminatory Compliance: How LLMs Answer Queries from Protected Groups cites this paper.

Discriminatory Compliance: How LLMs Answer Queries from Protected Groups SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal

Reference 106

Resolution: verified exact; arxiv_id, observed 2026-06-26T12:59:29.405506Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation b860b720-92ce-4383-9e4d-59ea998a0212 · inbound

PHANTOM: A Large-Scale Dataset of Multimodal Adversarial Attacks for Vision-Language Models cites this paper.

PHANTOM: A Large-Scale Dataset of Multimodal Adversarial Attacks for Vision-Language Models SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal

Reference 11

Resolution: metadata mismatch; arxiv_id, observed 2026-07-04T17:09:59.500402Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation bcc533d1-39a6-4439-9ad0-f61a47f1db0b · inbound

Do Encoders Suffice? A Systematic Comparison of Encoder and Decoder Safety Judges for LLM Adversarial Evaluation cites this paper.

Do Encoders Suffice? A Systematic Comparison of Encoder and Decoder Safety Judges for LLM Adversarial Evaluation SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal

Reference 16

Resolution: verified exact; arxiv_id, observed 2026-07-04T20:00:07.985799Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 19a1a96f-8173-463b-ac50-a83ed3eff9b3 · inbound

Agentic Abstention: Do Agents Know When to Stop Instead of Act? cites this paper.

Agentic Abstention: Do Agents Know When to Stop Instead of Act? SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal

Reference 61

Resolution: metadata mismatch; arxiv_id, observed 2026-06-30T09:54:34.380647Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 4816bf2f-87a9-4924-8233-5347664420a4 · inbound

Addressing Over-Refusal in LLMs with Competing Rewards cites this paper.

Addressing Over-Refusal in LLMs with Competing Rewards SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal

Reference 34

Resolution: verified exact; arxiv_id, observed 2026-07-01T07:05:29.223049Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 0aeee549-91e6-40e4-a8b4-d131e713f3eb · inbound

Not All Refusals Are Equal: How Safety Alignment Fails Cybersecurity at Scale cites this paper.

Not All Refusals Are Equal: How Safety Alignment Fails Cybersecurity at Scale SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal

Reference 16

Resolution: unresolved; no resolver link, observed 2026-07-12T07:33:43.015966Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2579c87e-8a8f-4c25-bc4e-2702148f01ed · inbound

BioTIER: A Refusal Benchmark for Targeted Biological Risk Mitigation cites this paper.

BioTIER: A Refusal Benchmark for Targeted Biological Risk Mitigation SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-02T02:00:44.842416Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0d12b4db-f03f-48e6-83eb-facc8d89715b · inbound

How Jailbreak Attacks Inform Safety Alignment: A Defender-Centric, Shapley-Based Evaluation of Jailbreak Contributions cites this paper.

How Jailbreak Attacks Inform Safety Alignment: A Defender-Centric, Shapley-Based Evaluation of Jailbreak Contributions SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-01T18:54:57.199932Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1805f2bd-03c7-4e0c-856d-5a072c199b0c · inbound

Fence: Specialized SLM Guardrails for LLM Applications cites this paper.

Fence: Specialized SLM Guardrails for LLM Applications SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-02T13:21:55.083013Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9066c1b2-ab38-40eb-9c4c-92a390a3db51 · inbound

Architectural Backdoors in Vision-Language Model Supply Chains via Representation Steering cites this paper.

Architectural Backdoors in Vision-Language Model Supply Chains via Representation Steering SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-01T02:23:11.890673Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bb055c66-c166-43b2-9b36-00df8cf1e36f · inbound

AISPA: User-Centric System Prompt Auditing for Large Language Model Applications cites this paper.

AISPA: User-Centric System Prompt Auditing for Large Language Model Applications SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal

Reference 20

Resolution: unresolved; no resolver link, observed 2026-07-31T02:04:06.864702Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b050bf87-bc25-450d-993d-c098885d63cf · inbound

Chain-of-Models: Cross-Model Auditing for Bias-Robust LLM Judges cites this paper.

Chain-of-Models: Cross-Model Auditing for Bias-Robust LLM Judges SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-03T00:55:22.240966Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.