OR-Bench: An Over-Refusal Benchmark for Large Language Models | Paper Citation Record

Observation f5fbc348-805f-4b93-a464-09b387ca7d86 · inbound

Probing the limitations of multimodal language models for chemistry and materials research cites this paper.

Probing the limitations of multimodal language models for chemistry and materials research OR-Bench: An Over-Refusal Benchmark for Large Language Models

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-12T12:45:35.737949Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 942dcb84-786d-4c22-bd38-cb4889430a4b · inbound

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

Refusal Tokens: A Simple Way to Calibrate Refusals in Large Language Models OR-Bench: An Over-Refusal Benchmark for Large Language Models

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-11T19:25:04.775042Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7490d506-06b8-4faf-97c7-129aafd999db · inbound

Semantic Loss Guided Data Efficient Supervised Fine Tuning for Safe Responses in LLMs cites this paper.

Semantic Loss Guided Data Efficient Supervised Fine Tuning for Safe Responses in LLMs OR-Bench: An Over-Refusal Benchmark for Large Language Models

Reference 2021

Resolution: unresolved; no resolver link, observed 2026-08-11T20:33:59.615309Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 56584722-6f9e-41f6-9f3f-90cb256a0fd9 · inbound

Open Problems in Machine Unlearning for AI Safety cites this paper.

Open Problems in Machine Unlearning for AI Safety OR-Bench: An Over-Refusal Benchmark for Large Language Models

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-10T21:24:10.025794Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c3d2d205-09e5-4a0b-97cd-8aebf7d70fa7 · inbound

FairCoder: Probing LLM Bias in High-Stakes Decision Making via Coding Tasks cites this paper.

FairCoder: Probing LLM Bias in High-Stakes Decision Making via Coding Tasks OR-Bench: An Over-Refusal Benchmark for Large Language Models

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-10T21:18:01.315075Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c530ab1e-d492-41e7-8627-266a1c0dfe3b · inbound

Latent-space adversarial training with post-aware calibration for defending large language models against jailbreak attacks cites this paper.

Latent-space adversarial training with post-aware calibration for defending large language models against jailbreak attacks OR-Bench: An Over-Refusal Benchmark for Large Language Models

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-10T19:08:01.608940Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2c8e0039-a1d6-498f-ac5e-f3b0c5d995c2 · inbound

CASE-Bench: Context-Aware SafEty Benchmark for Large Language Models cites this paper.

CASE-Bench: Context-Aware SafEty Benchmark for Large Language Models OR-Bench: An Over-Refusal Benchmark for Large Language Models

Reference 2013

Resolution: unresolved; no resolver link, observed 2026-08-10T14:51:58.746774Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a6962c30-7769-4013-9981-9a9c3537f56b · inbound

Position: Adversarial ML for LLMs Is Not Making Any Progress cites this paper.

Position: Adversarial ML for LLMs Is Not Making Any Progress OR-Bench: An Over-Refusal Benchmark for Large Language Models

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-09T12:47:21.642807Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e67b5b15-8613-41b6-8f52-7b5cf9eaefc6 · inbound

Forbidden Science: Dual-Use AI Challenge Benchmark and Scientific Refusal Tests cites this paper.

Forbidden Science: Dual-Use AI Challenge Benchmark and Scientific Refusal Tests OR-Bench: An Over-Refusal Benchmark for Large Language Models

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-08T19:21:19.126985Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1700476e-fa02-4fb5-b33e-7ea86dd76dd5 · inbound

JBShield: Defending Large Language Models from Jailbreak Attacks through Activated Concept Analysis and Manipulation cites this paper.

JBShield: Defending Large Language Models from Jailbreak Attacks through Activated Concept Analysis and Manipulation OR-Bench: An Over-Refusal Benchmark for Large Language Models

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-08T12:25:30.547187Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9b20750b-9e2c-47e2-ad85-3430e0d371e9 · inbound

The Hidden Dimensions of LLM Alignment: A Multi-Dimensional Analysis of Orthogonal Safety Directions cites this paper.

The Hidden Dimensions of LLM Alignment: A Multi-Dimensional Analysis of Orthogonal Safety Directions OR-Bench: An Over-Refusal Benchmark for Large Language Models

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-07T23:08:02.240706Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b55a4152-bee3-447d-aa84-fe646c1e8a6b · inbound

LLM-Safety Evaluations Lack Robustness cites this paper.

LLM-Safety Evaluations Lack Robustness OR-Bench: An Over-Refusal Benchmark for Large Language Models

Reference 19

Resolution: verified exact; arxiv_id, observed 2026-05-23T01:27:21.424406Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation a90b09ef-8ac4-4e71-876e-b7d460e28410 · inbound

DETAM: Defending LLMs Against Jailbreak Attacks via Targeted Attention Modification cites this paper.

DETAM: Defending LLMs Against Jailbreak Attacks via Targeted Attention Modification OR-Bench: An Over-Refusal Benchmark for Large Language Models

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-16T12:10:30.948693Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a6fd153e-26cb-405d-a1e7-45419fbf37a7 · inbound

aiXamine: Simplified LLM Safety and Security cites this paper.

aiXamine: Simplified LLM Safety and Security OR-Bench: An Over-Refusal Benchmark for Large Language Models

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-16T11:39:10.716090Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0fa683eb-bdc3-41b1-8e9d-19f464270ddd · inbound

FalseReject: A Resource for Improving Contextual Safety and Mitigating Over-Refusals in LLMs via Structured Reasoning cites this paper.

FalseReject: A Resource for Improving Contextual Safety and Mitigating Over-Refusals in LLMs via Structured Reasoning OR-Bench: An Over-Refusal Benchmark for Large Language Models

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-15T22:10:09.270342Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0758b737-4732-4884-9924-d4b18d25fad9 · inbound

Relative Bias: A Comparative Framework for Quantifying Bias in LLMs cites this paper.

Relative Bias: A Comparative Framework for Quantifying Bias in LLMs OR-Bench: An Over-Refusal Benchmark for Large Language Models

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-07T15:12:19.066466Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3ada40e2-6b9b-427a-82a7-f2956c25f27c · inbound

Beyond Safe Answers: A Benchmark for Evaluating True Risk Awareness in Large Reasoning Models cites this paper.

Beyond Safe Answers: A Benchmark for Evaluating True Risk Awareness in Large Reasoning Models OR-Bench: An Over-Refusal Benchmark for Large Language Models

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-07T14:13:52.566860Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 85030306-0453-4f53-ba6c-4f12428412b5 · inbound

VSCBench: Bridging the Gap in Vision-Language Model Safety Calibration cites this paper.

VSCBench: Bridging the Gap in Vision-Language Model Safety Calibration OR-Bench: An Over-Refusal Benchmark for Large Language Models

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-07T14:13:10.702663Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2af4f3a5-2938-40c3-be36-2ef53c711183 · inbound

Multi-objective Large Language Model Alignment with Hierarchical Experts cites this paper.

Multi-objective Large Language Model Alignment with Hierarchical Experts OR-Bench: An Over-Refusal Benchmark for Large Language Models

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-07T13:52:09.068357Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bd4cb0c8-2ab2-4de2-ac79-4773c7df3b74 · inbound

ReGA: Model-Based Safeguard for LLMs via Representation-Guided Abstraction cites this paper.

ReGA: Model-Based Safeguard for LLMs via Representation-Guided Abstraction OR-Bench: An Over-Refusal Benchmark for Large Language Models

Reference 56

Resolution: verified exact; arxiv_id, observed 2026-05-19T11:37:15.914531Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation f366d40f-8412-423a-8efd-6d89fba3a5ef · inbound

MidPO: Dual Preference Optimization for Safety and Helpfulness in Large Language Models via a Mixture of Experts Framework cites this paper.

MidPO: Dual Preference Optimization for Safety and Helpfulness in Large Language Models via a Mixture of Experts Framework OR-Bench: An Over-Refusal Benchmark for Large Language Models

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-07T11:29:01.068351Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 14de37fd-3c28-4821-adbe-efc2d4d0a818 · inbound

From Rogue to Safe AI: The Role of Explicit Refusals in Aligning LLMs with International Humanitarian Law cites this paper.

From Rogue to Safe AI: The Role of Explicit Refusals in Aligning LLMs with International Humanitarian Law OR-Bench: An Over-Refusal Benchmark for Large Language Models

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-07T10:28:54.986950Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d3887f60-c7e8-49ca-b717-bf18f935a22d · inbound

SafeCoT: Improving VLM Safety with Minimal Reasoning cites this paper.

SafeCoT: Improving VLM Safety with Minimal Reasoning OR-Bench: An Over-Refusal Benchmark for Large Language Models

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-07T05:18:59.574137Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 245fc8a6-5db8-4ccb-8ce6-e13192ca047c · inbound

Just Enough Shifts: Mitigating Over-Refusal in Aligned Language Models with Targeted Representation Fine-Tuning cites this paper.

Just Enough Shifts: Mitigating Over-Refusal in Aligned Language Models with Targeted Representation Fine-Tuning OR-Bench: An Over-Refusal Benchmark for Large Language Models

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-06T19:57:43.629886Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cae4b572-6abc-48c8-bd49-80ef44374df2 · inbound

LLMs Encode Harmfulness and Refusal Separately cites this paper.

LLMs Encode Harmfulness and Refusal Separately OR-Bench: An Over-Refusal Benchmark for Large Language Models

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-06T17:03:15.633680Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 553347cf-8323-4ce0-8d54-573938d47ef4 · inbound

Beyond Surface-Level Detection: Towards Cognitive-Driven Defense Against Jailbreak Attacks via Meta-Operations Reasoning cites this paper.

Beyond Surface-Level Detection: Towards Cognitive-Driven Defense Against Jailbreak Attacks via Meta-Operations Reasoning OR-Bench: An Over-Refusal Benchmark for Large Language Models

Reference 149

Resolution: unresolved; no resolver link, observed 2026-08-06T04:47:25.517815Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2a28ee14-ff1e-4212-a162-936697886bee · inbound

ORFuzz: Fuzzing the "Other Side" of LLM Safety -- Testing Over-Refusal cites this paper.

ORFuzz: Fuzzing the "Other Side" of LLM Safety -- Testing Over-Refusal OR-Bench: An Over-Refusal Benchmark for Large Language Models

Reference 8

Resolution: verified exact; arxiv_id, observed 2026-05-18T23:31:54.602048Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 6dc443b8-3a12-41f1-addc-a74c324002bf · inbound

No for Some, Yes for Others: Persona Prompts and Other Sources of False Refusal in Language Models cites this paper.

No for Some, Yes for Others: Persona Prompts and Other Sources of False Refusal in Language Models OR-Bench: An Over-Refusal Benchmark for Large Language Models

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-04T21:22:14.290904Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 93cf701d-1912-4476-9664-f2189ee9d5b2 · inbound

Not All Needles Are Found: How Fact Distribution and Don't Make It Up Prompts Shape Retrieval, Reasoning, and Hallucination in Long-Context LLMs cites this paper.

Not All Needles Are Found: How Fact Distribution and Don't Make It Up Prompts Shape Retrieval, Reasoning, and Hallucination in Long-Context LLMs OR-Bench: An Over-Refusal Benchmark for Large Language Models

Reference 89

Resolution: unresolved; no resolver link, observed 2026-08-03T12:42:38.838889Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 871570c7-db20-4069-af6f-8f8071b41550 · inbound

Analysing Differences in Persuasive Language in LLM-Generated Text: Uncovering Stereotypical Gender Patterns cites this paper.

Analysing Differences in Persuasive Language in LLM-Generated Text: Uncovering Stereotypical Gender Patterns OR-Bench: An Over-Refusal Benchmark for Large Language Models

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-03T11:35:39.627069Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7750d229-a914-4ecf-96d5-e216c4dfecc0 · inbound

RACC: Representation-Aware Coverage Criteria for LLM Safety Testing cites this paper.

RACC: Representation-Aware Coverage Criteria for LLM Safety Testing OR-Bench: An Over-Refusal Benchmark for Large Language Models

Reference 16

Resolution: verified exact; arxiv_id, observed 2026-05-16T08:17:36.646432Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 1c22e9c0-1e31-49c9-85d9-05b0b27cb9f3 · inbound

Robust Policy Optimization to Prevent Catastrophic Forgetting cites this paper.

Robust Policy Optimization to Prevent Catastrophic Forgetting OR-Bench: An Over-Refusal Benchmark for Large Language Models

Reference 13

Resolution: verified exact; arxiv_id, observed 2026-05-16T05:37:24.313558Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation cf3358a2-13d2-4260-a988-dfd0c2063134 · inbound

Power and Limitations of Aggregation in Compound AI Systems cites this paper.

Power and Limitations of Aggregation in Compound AI Systems OR-Bench: An Over-Refusal Benchmark for Large Language Models

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-02T21:09:49.563604Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 02b49cf3-1707-4c19-a26b-164617b8a9ef · inbound

SelfGrader: LLM Jailbreak Detection via Anchored Token-Level Logits cites this paper.

SelfGrader: LLM Jailbreak Detection via Anchored Token-Level Logits OR-Bench: An Over-Refusal Benchmark for Large Language Models

Reference 5

Resolution: verified exact; arxiv_id, observed 2026-05-13T21:48:19.437868Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation c62b8c9d-7145-4eb7-a75e-aa14cfe5e50e · 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 OR-Bench: An Over-Refusal Benchmark for Large Language Models

Reference 7

Resolution: verified exact; arxiv_id, observed 2026-05-13T19:28:09.938746Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 76979c98-1866-4261-ad43-e1aa012fc0f1 · 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 OR-Bench: An Over-Refusal Benchmark for Large Language Models

Reference 10

Resolution: verified exact; arxiv_id, observed 2026-05-11T00:35:52.516530Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation fac9a0e5-6f66-49ac-8b5b-ccb6562af93c · 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 OR-Bench: An Over-Refusal Benchmark for Large Language Models

Reference 10

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 bb565363-ccb2-4e0f-be8f-cf4d6bcbb223 · inbound

Refute-or-Promote: An Adversarial Stage-Gated Multi-Agent Review Methodology for High-Precision LLM-Assisted Defect Discovery cites this paper.

Refute-or-Promote: An Adversarial Stage-Gated Multi-Agent Review Methodology for High-Precision LLM-Assisted Defect Discovery OR-Bench: An Over-Refusal Benchmark for Large Language Models

Reference 32

Resolution: verified exact; arxiv_id, observed 2026-05-10T03:14:08.024390Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation cc58d492-46c4-4f46-9699-b298b3cc5160 · inbound

Knowledge Distillation Must Account for What It Loses cites this paper.

Knowledge Distillation Must Account for What It Loses OR-Bench: An Over-Refusal Benchmark for Large Language Models

Reference 41

Resolution: verified exact; arxiv_id, observed 2026-05-11T23:26:18.660235Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation a0c6fad7-ca75-4fce-9784-7c3450e92ee2 · inbound

Knowledge Distillation Must Account for What It Loses cites this paper.

Knowledge Distillation Must Account for What It Loses OR-Bench: An Over-Refusal Benchmark for Large Language Models

Reference 41

Resolution: verified exact; arxiv_id, observed 2026-05-11T22:01:13.526306Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 5f9105b3-2973-49d7-abaa-e88601ad6349 · inbound

Disentangling Intent from Role: Adversarial Self-Play for Persona-Invariant Safety Alignment cites this paper.

Disentangling Intent from Role: Adversarial Self-Play for Persona-Invariant Safety Alignment OR-Bench: An Over-Refusal Benchmark for Large Language Models

Reference 49

Resolution: verified exact; arxiv_id, observed 2026-05-11T16:21:07.419924Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 7a09cf8e-8d6d-4c43-ac3a-5df817ba9e1f · inbound

Latent Personality Alignment: Improving Harmlessness Without Mentioning Harms cites this paper.

Latent Personality Alignment: Improving Harmlessness Without Mentioning Harms OR-Bench: An Over-Refusal Benchmark for Large Language Models

Reference 4

Resolution: verified exact; arxiv_id, observed 2026-05-12T07:51:43.562457Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 89801801-ac87-427f-9977-2cfc2f76e90a · inbound

EquiMem: Calibrating Shared Memory in Multi-Agent Debate via Game-Theoretic Equilibrium cites this paper.

EquiMem: Calibrating Shared Memory in Multi-Agent Debate via Game-Theoretic Equilibrium OR-Bench: An Over-Refusal Benchmark for Large Language Models

Reference 14

Resolution: verified exact; arxiv_id, observed 2026-05-12T05:56:26.309530Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 2cbda156-ec48-46de-92e9-fed450dadf5a · inbound

Taxonomy and Consistency Analysis of Safety Benchmarks for AI Agents cites this paper.

Taxonomy and Consistency Analysis of Safety Benchmarks for AI Agents OR-Bench: An Over-Refusal Benchmark for Large Language Models

Reference 8

Resolution: verified exact; arxiv_id, observed 2026-05-21T01:43:56.924885Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 757b7704-4f27-4c1d-9dd3-cfca173d462b · 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 OR-Bench: An Over-Refusal Benchmark for Large Language Models

Reference 14

Resolution: verified exact; arxiv_id, observed 2026-05-22T01:20:51.889010Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 5af05fa0-c542-49d7-9279-4c1efac0af7e · inbound

Palette: A Modular, Controllable, and Efficient Framework for On-demand Authorized Safety Alignment Relaxation in LLMs cites this paper.

Palette: A Modular, Controllable, and Efficient Framework for On-demand Authorized Safety Alignment Relaxation in LLMs OR-Bench: An Over-Refusal Benchmark for Large Language Models

Reference 51

Resolution: verified exact; arxiv_id, observed 2026-06-30T16:04:52.628366Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 5c988fe2-ee8a-4724-ac32-bb8ab070abe3 · inbound

Ellipsoid Control: A White-list Jailbreak Defense via Benign Latent Modeling cites this paper.

Ellipsoid Control: A White-list Jailbreak Defense via Benign Latent Modeling OR-Bench: An Over-Refusal Benchmark for Large Language Models

Reference 15

Resolution: verified exact; arxiv_id, observed 2026-06-30T13:14:40.779901Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 416ab8e3-2843-41ef-b8fb-b57381d80de1 · inbound

The Ethics of LLM Sandbox and Persona Dynamics cites this paper.

The Ethics of LLM Sandbox and Persona Dynamics OR-Bench: An Over-Refusal Benchmark for Large Language Models

Reference 4

Resolution: metadata mismatch; arxiv_id, observed 2026-06-29T12:43:25.126621Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation bb8d5d0a-b010-4562-95f8-aef7057d4e39 · 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 OR-Bench: An Over-Refusal Benchmark for Large Language Models

Reference 6

Resolution: verified exact; arxiv_id, observed 2026-06-29T09:13:15.991497Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation bb7074f5-398f-4098-bd1a-22c6caf3c5ac · inbound

Triaging Threats to Specialized Guardrails cites this paper.

Triaging Threats to Specialized Guardrails OR-Bench: An Over-Refusal Benchmark for Large Language Models

Reference 5

Resolution: verified exact; arxiv_id, observed 2026-06-28T22:32:44.346641Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 48e132d9-c9a1-4161-b6c8-3f39f5c8e78b · inbound

Understanding the Self-Reflection Mechanisms of LLMs through Biased Attitude Associations cites this paper.

Understanding the Self-Reflection Mechanisms of LLMs through Biased Attitude Associations OR-Bench: An Over-Refusal Benchmark for Large Language Models

Reference 31

Resolution: metadata mismatch; arxiv_id, observed 2026-07-01T20:36:12.167986Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation ab1d4848-967d-44de-8620-232ccbf4e0c7 · inbound

Dialectics of Alignment: Harnessing Unsafe Knowledge for Dynamic Safety Routing cites this paper.

Dialectics of Alignment: Harnessing Unsafe Knowledge for Dynamic Safety Routing OR-Bench: An Over-Refusal Benchmark for Large Language Models

Reference 15

Resolution: verified exact; arxiv_id, observed 2026-06-28T19:32:34.575384Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation f8aebd10-570b-44a8-9058-8b3904623bdf · inbound

Designing for Doubt: The Case for Informed Abstention in Autonomous Agents cites this paper.

Designing for Doubt: The Case for Informed Abstention in Autonomous Agents OR-Bench: An Over-Refusal Benchmark for Large Language Models

Reference 4

Resolution: verified exact; arxiv_id, observed 2026-07-01T23:46:23.700019Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation f98cd193-7c9e-47f8-aa79-a8edcb84d1bf · inbound

FLIPS: Instance-Fingerprinting for LLMs via Pseudo-random Sequences cites this paper.

FLIPS: Instance-Fingerprinting for LLMs via Pseudo-random Sequences OR-Bench: An Over-Refusal Benchmark for Large Language Models

Reference 52

Resolution: metadata mismatch; arxiv_id, observed 2026-07-02T01:56:27.942088Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation ad9524b8-ea57-4769-8479-65d9d013ab76 · inbound

CHASE: Adversarial Red-Blue Teaming for Improving LLM Safety using Reinforcement Learning cites this paper.

CHASE: Adversarial Red-Blue Teaming for Improving LLM Safety using Reinforcement Learning OR-Bench: An Over-Refusal Benchmark for Large Language Models

Reference 45

Resolution: metadata mismatch; arxiv_id, observed 2026-07-02T12:06:55.639498Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 4246cc48-4cb6-4ab8-93a2-1fba21e54237 · inbound

Auditing Proprietary Alignment in Large Language Models: A Comparative Framework Without a Ground-Truth Standard cites this paper.

Auditing Proprietary Alignment in Large Language Models: A Comparative Framework Without a Ground-Truth Standard OR-Bench: An Over-Refusal Benchmark for Large Language Models

Reference 5

Resolution: metadata mismatch; arxiv_id, observed 2026-07-02T22:17:26.020107Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation d3931b56-9828-4521-9892-854c1e7ed77b · inbound

PsychoSafe: Eliciting Psychologically-Informed Refusals in Large Language Models cites this paper.

PsychoSafe: Eliciting Psychologically-Informed Refusals in Large Language Models OR-Bench: An Over-Refusal Benchmark for Large Language Models

Reference 2

Resolution: verified exact; arxiv_id, observed 2026-07-03T01:27:31.228542Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 128ae228-7814-421e-95c1-653d2b133968 · inbound

An LLM-Native Psychometric Instrument Reveals a Self-Report--Behavior Gap Across 25 Models cites this paper.

An LLM-Native Psychometric Instrument Reveals a Self-Report--Behavior Gap Across 25 Models OR-Bench: An Over-Refusal Benchmark for Large Language Models

Reference 5

Resolution: verified exact; arxiv_id, observed 2026-07-04T19:50:09.966245Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 02c3ae61-49c3-4c53-967b-73e436e652e1 · inbound

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

Sch\"utzen: Evaluating LLM Safety in Bulgarian and German Contexts OR-Bench: An Over-Refusal Benchmark for Large Language Models

Reference 16

Resolution: verified exact; arxiv_id, observed 2026-07-03T04:57:38.390307Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 829039a5-9561-4f0f-8276-604a52c9b12d · inbound

Muse Spark Safety & Preparedness Report cites this paper.

Muse Spark Safety & Preparedness Report OR-Bench: An Over-Refusal Benchmark for Large Language Models

Reference 73

Resolution: metadata mismatch; arxiv_id, observed 2026-06-30T19:55:01.558009Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 8e0ad023-5950-4a2d-9d13-8aaed034aadb · inbound

From Refusal Geometry to Safety Geometry: Harmfulness--Refusal Coupling under Dynamic Adversarial Fine-Tuning cites this paper.

From Refusal Geometry to Safety Geometry: Harmfulness--Refusal Coupling under Dynamic Adversarial Fine-Tuning OR-Bench: An Over-Refusal Benchmark for Large Language Models

Reference 15

Resolution: unresolved; no resolver link, observed 2026-07-12T13:51:23.302296Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9af1926e-30cb-4dd5-ac00-53824bc8a398 · inbound

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

Discriminatory Compliance: How LLMs Answer Queries from Protected Groups OR-Bench: An Over-Refusal Benchmark for Large Language Models

Reference 104

Resolution: metadata mismatch; arxiv_id, observed 2026-06-26T12:59:29.372405Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 5b5acc47-0346-407d-8bf6-be5966ab85d1 · inbound

At the Edge of Understanding: Sparse Autoencoders Trace The Limits of Transformer Generalization cites this paper.

At the Edge of Understanding: Sparse Autoencoders Trace The Limits of Transformer Generalization OR-Bench: An Over-Refusal Benchmark for Large Language Models

Reference 2

Resolution: metadata mismatch; arxiv_id, observed 2026-07-04T15:49:56.284738Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 92957cf9-1ae4-4cc4-b834-f68eedbeaf05 · inbound

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

Addressing Over-Refusal in LLMs with Competing Rewards OR-Bench: An Over-Refusal Benchmark for Large Language Models

Reference 36

Resolution: metadata mismatch; arxiv_id, observed 2026-07-01T08:55:35.559051Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 2dff7a81-6bd7-42df-a1c0-b554c3131951 · inbound

OpenSafeIntent: Evaluating Intent-Calibrated Safe Completion Across Dual-Use Prompt Sets cites this paper.

OpenSafeIntent: Evaluating Intent-Calibrated Safe Completion Across Dual-Use Prompt Sets OR-Bench: An Over-Refusal Benchmark for Large Language Models

Reference 38

Resolution: metadata mismatch; arxiv_id, observed 2026-07-03T14:48:32.499370Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation b951f89c-121b-4456-b48b-850bf11e9d12 · inbound

Faithfulness to Refusal: A Causal Audit of Neuron Selectors cites this paper.

Faithfulness to Refusal: A Causal Audit of Neuron Selectors OR-Bench: An Over-Refusal Benchmark for Large Language Models

Reference 8

Resolution: verified exact; local_arxiv, observed 2026-07-07T15:43:53.889765Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation b1e0bd40-6d38-48f1-b9a5-2a90a79377b5 · inbound

BioSecBench-Refusal: A paired metric for performance and alignment in agentic biosecurity risk assessment cites this paper.

BioSecBench-Refusal: A paired metric for performance and alignment in agentic biosecurity risk assessment OR-Bench: An Over-Refusal Benchmark for Large Language Models

Reference 11

Resolution: unresolved; no resolver link, observed 2026-07-11T16:42:49.284801Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 22a13f1a-389d-48ae-8847-14d41dbd3c08 · inbound

BioSecBench-Refusal: A paired metric for performance and alignment in agentic biosecurity risk assessment cites this paper.

BioSecBench-Refusal: A paired metric for performance and alignment in agentic biosecurity risk assessment OR-Bench: An Over-Refusal Benchmark for Large Language Models

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-02T08:40:01.376681Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 207ba283-9daa-4759-b969-cd7ae44ab2bb · inbound

Beyond Refusal: A Same-Lineage Study of Aligned and Abliterated LLMs for Vulnerability Analysis cites this paper.

Beyond Refusal: A Same-Lineage Study of Aligned and Abliterated LLMs for Vulnerability Analysis OR-Bench: An Over-Refusal Benchmark for Large Language Models

Reference 48

Resolution: verified exact; local_arxiv, observed 2026-07-08T23:05:44.269506Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 7dfadebb-76e8-40ed-b95f-16bce40796b8 · inbound

Efficient Safety Alignment of Language Models via Latent Personality Traits cites this paper.

Efficient Safety Alignment of Language Models via Latent Personality Traits OR-Bench: An Over-Refusal Benchmark for Large Language Models

Reference 9

Resolution: verified exact; local_arxiv, observed 2026-07-10T15:27:20.069606Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 7878eb1a-ca62-4cfa-b872-3e92ccb11110 · inbound

The Entanglement Wall: Activation-Space Probes as Risk Detectors, Not Context Adjudicators cites this paper.

The Entanglement Wall: Activation-Space Probes as Risk Detectors, Not Context Adjudicators OR-Bench: An Over-Refusal Benchmark for Large Language Models

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-02T07:09:30.211340Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation af5421f9-5c79-4bd3-909e-28d7a610d778 · inbound

Phantom Guardrails: When Self-Improving Agent Harnesses Fix Failures That Never Happened cites this paper.

Phantom Guardrails: When Self-Improving Agent Harnesses Fix Failures That Never Happened OR-Bench: An Over-Refusal Benchmark for Large Language Models

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-02T07:01:19.315752Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0563645b-47ff-484d-8501-2a3c15a323ca · inbound

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

BioTIER: A Refusal Benchmark for Targeted Biological Risk Mitigation OR-Bench: An Over-Refusal Benchmark for Large Language Models

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-02T02:00:44.107363Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f3c78e28-65a4-4ac9-bba3-b905b48479f0 · inbound

BioSecBench-Surveillance: A Verifiable Benchmark for AI Agents in Pathogen Genomic Surveillance cites this paper.

BioSecBench-Surveillance: A Verifiable Benchmark for AI Agents in Pathogen Genomic Surveillance OR-Bench: An Over-Refusal Benchmark for Large Language Models

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-01T12:58:37.815384Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f0ff384a-1a37-40d2-8b34-08f71e9c1d02 · inbound

Robust Critics: Defending LLMs Against Multi-Turn Attacks cites this paper.

Robust Critics: Defending LLMs Against Multi-Turn Attacks OR-Bench: An Over-Refusal Benchmark for Large Language Models

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-02T13:17:49.660643Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0ff948cf-d26d-4f60-a12e-a822a37046d2 · inbound

Test-Time Scaling via Error Localization cites this paper.

Test-Time Scaling via Error Localization OR-Bench: An Over-Refusal Benchmark for Large Language Models

Reference 124

Resolution: unresolved; no resolver link, observed 2026-08-01T07:28:30.527305Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 75a6e83e-7179-488d-8857-cf1a5ded795f · inbound

When LLM Defenses Backfire: Characterizing Safety, Performance, and Cost Trade-offs cites this paper.

When LLM Defenses Backfire: Characterizing Safety, Performance, and Cost Trade-offs OR-Bench: An Over-Refusal Benchmark for Large Language Models

Reference 7

Resolution: unresolved; no resolver link, observed 2026-07-31T16:06:04.281114Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3a627b25-8f8e-4132-9e5c-bf5bdcaa04f8 · inbound

RoCo-ACE: Rollout-Conditioned Online Distillation for Retention-Aware Knowledge Injection cites this paper.

RoCo-ACE: Rollout-Conditioned Online Distillation for Retention-Aware Knowledge Injection OR-Bench: An Over-Refusal Benchmark for Large Language Models

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-02T11:50:16.270164Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0514d179-cc17-43db-a904-b8f65dc95d1f · inbound

MMOOC: A Comprehensive Benchmark for Out-of-Context Evaluation in Multimodal Large Language Models cites this paper.

MMOOC: A Comprehensive Benchmark for Out-of-Context Evaluation in Multimodal Large Language Models OR-Bench: An Over-Refusal Benchmark for Large Language Models

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-04T01:23:34.580270Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e455945e-cebc-4316-9511-2d374ae73313 · inbound

Safety, or Just Capability? A Validity Audit of Agent-Safety Benchmarks cites this paper.

Safety, or Just Capability? A Validity Audit of Agent-Safety Benchmarks OR-Bench: An Over-Refusal Benchmark for Large Language Models

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-03T00:45:59.446555Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 58f0fcc2-0fb7-4eac-9743-37fcf82efc48 · inbound

Single Canonical Prompts Underestimate LLM Safety's Surface-Form Sensitivity cites this paper.

Single Canonical Prompts Underestimate LLM Safety's Surface-Form Sensitivity OR-Bench: An Over-Refusal Benchmark for Large Language Models

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-05T00:48:47.873645Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1bce99af-8df6-4e4b-99a9-dc0a3aba4e36 · inbound

Item Response Theory for AI Safety cites this paper.

Item Response Theory for AI Safety OR-Bench: An Over-Refusal Benchmark for Large Language Models

Reference 1981

Resolution: unresolved; no resolver link, observed 2026-08-06T05:39:49.404749Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c4e08202-2970-4b86-b433-629d5dcce9ea · inbound

How Should I Pick a Foundation Model for My Robot? In Favor of a Community Evaluation Framework for Social Robots cites this paper.

How Should I Pick a Foundation Model for My Robot? In Favor of a Community Evaluation Framework for Social Robots OR-Bench: An Over-Refusal Benchmark for Large Language Models

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-10T18:49:33.723144Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1732f4de-e3f7-48e6-a487-20841a7b14d7 · inbound

Refusing Intent, Not Form: Wrapper-Based Intent-Group Supervision for LLM Safety cites this paper.

Refusing Intent, Not Form: Wrapper-Based Intent-Group Supervision for LLM Safety OR-Bench: An Over-Refusal Benchmark for Large Language Models

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-14T14:12:28.356256Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers