RefusalBench: Why Refusal Rate Misranks Frontier LLMs on Biological Research Prompts

• URL: http://arxiv.org/abs/2605.21545v1
• Date: Wed, 20 May 2026 09:53:31 GMT
• Title: RefusalBench: Why Refusal Rate Misranks Frontier LLMs on Biological Research Prompts
• Abstract summary: Strict refusal rates span 0.1% to 94.6% on identical prompts.<n>Nine of 18 frontier models exhibit a hedge-but-help partial-compliance pattern at dual-use tier that binary refusal metrics cannot detect.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Frontier large language models are increasingly deployed as orchestration backbones for biological research workflows, yet no shared evidence base exists for comparing their refusal behaviour on legitimate research prompts. RefusalBench, introduced here, is a matched-triple benchmark of 141 prompts in 47 bundles that holds task framing constant while varying only biological risk tier (benign, borderline, dual-use), enabling tier-conditioned comparisons robust to subdomain confounding. A 15-prompt should-refuse positive-control module establishes per-model calibration floors; three models fail to refuse even these prompts. Across 19 frontier models in the May 2026 snapshot, strict refusal rates span 0.1% to 94.6% on identical prompts. Jurisdiction does not predict refusal in this snapshot (Mann-Whitney U, p = 0.393; EU n = 1, US bimodal); provider identity does, with Anthropic's API stack predicting refusal at OR = 21.03 (95% CI: 14.58-30.34 prompt-clustered; 5.70-77.55 under model-clustered GEE). This effect is best read as access-path-level rather than model-weight-level: 99.8% of Anthropic's strict refusals carry the same safety_policy adjudicated reason code, consistent with a small set of canonical refusal templates rather than case-by-case model reasoning. Strict refusal rate misranks safety calibration: Grok 4.20 achieves the highest tier discrimination (Youden's J = 0.787) while ranking only seventh by overall refusal rate, and Claude Opus 4.7's J dropped 65% from prior versions with no improvement in dual-use detection. Nine of 18 frontier models exhibit a hedge-but-help partial-compliance pattern at dual-use tier that binary refusal metrics cannot detect.

Related papers

• Marginal Fidelity Does Not Establish User Simulation in Demographic Synthetic Survey Panels: Response Contracts, Support Collapse and Conditioning Failure [51.736723807086385]
  Population-marginal agreement is evidence about an elicitation contract and an estimand obtainable without simulated respondents, not evidence of individual simulation.<n>On nine aligned model-battery pairs, a no-persona population-prevalence query averages 6.27 MAE versus 12.39 for committed panels and wins all nine comparisons.
  arXiv  Detail & Related papers  (2026-09-07T10:22:22Z)
• Confidently Wrong: Exception Chain Collapse in Frontier LLM Rule Evaluation [0.0]
  We document a failure class in frontier large language models.<n>The failure reproduces at first observation, but its empirical surface is unstable.<n>For regulated, frontier-model accuracy is a moving compliance boundary that shifts without notice.
  arXiv  Detail & Related papers  (2026-07-25T22:40:02Z)
• Abliteration Is Not a Scalpel: Off-Target Effects of Refusal Removal on Decision Disposition Across Model Families [51.56484100374058]
  Abliteration - deleting a model's refusal direction from its weights - is the standard recipe behind popular "uncensored" open-weight models.<n>As a disposition probe we use 21,600 decisions under uncertainty, replayed through a frozen pipeline so the decision-layer model is the only variable.<n>Three effects replicate across both families (weeks-clustered CIs excluding zero)<n>A fourth effect reverses sign: the same operation makes Gemma-abliterated less confident and Qwen-abliterated more (family CIs non-overlapping)
  arXiv  Detail & Related papers  (2026-07-19T22:27:00Z)
• Speculative Decoding at Temperature Zero: A Scoped Safety-Invariance Screen with a 48,072-Sample Expansion [0.0]
  Speculative decoding accelerates inference by letting a draft model propose tokens for a target model to verify.<n>We show that at temperature zero, can draft-side behavior leak into safety-scored outputs?
  arXiv  Detail & Related papers  (2026-06-23T19:06:42Z)
• Knowledge Index of Noah's Ark [63.143852586221534]
  We introduce KINA, an 899-item benchmark across 261 fine-grained disciplines.<n>We prove a bonus-on-bar tournament weakly FOSD-dominates flat payment in released-review quality.<n>The top model, Gemini-3.1-Pro-Preview, reaches 53.17%, followed by Claude-Opus-4.6 at 49.92% and GPT-5.4 at 48.55%.
  arXiv  Detail & Related papers  (2026-06-03T17:06:49Z)
• When Hard Negatives Hurt: Bridging the Generative-Discriminative Gap in Hard Negative Synthesis for Retrieval [45.5843471557695]
  We show that naively incorporating generated negatives into contrastive learning often degrades retrieval performance.<n>Our analysis reveals two compounding failure modes: discriminative-agnostic generation and source-dependent shortcuts.<n>To close this gap, we propose CausalNeg consisting of two main modules.
  arXiv  Detail & Related papers  (2026-05-31T15:48:30Z)
• ContractBench: Can LLM Agents Preserve Observation Contracts? [9.057486468322933]
  We show that observation contract compliance is an emergent, regression-prone capability.<n>We introduce ContractBench, a benchmark of 33 dual-axis tasks that probe two failure modes.<n>We report four findings: (i) no evaluated model clears 80%, with Claude-Opus-4.6 leading at 77.8%; (ii) a sharp within-family capability cliff in Qwen 3.5 between 4B (0%) and 9B (56.6%), smoothing to 70.7% at 397B-A17B; (iii) non-monotonic scaling across the GPT-5 family: agentic post-training can erode
  arXiv  Detail & Related papers  (2026-05-17T06:37:04Z)
• Distributional Energy-Based Models for Uncertainty-Aware Structured LLM Reasoning [40.342912574072024]
  Large Language Models produce structured outputs such as travel plans or code solutions.<n>Individual reasoning steps may appear correct while the output as a whole violates budgets, fails test cases, or contradicts earlier deductions.<n>We propose a learned quality scorer with deterministic analytical constraint penalties for verifying structured LLM outputs.
  arXiv  Detail & Related papers  (2026-05-15T17:08:27Z)
• PBT-Bench: Benchmarking AI Agents on Property-Based Testing [29.035258104995204]
  We introduce PBT-Bench, a benchmark of 100 curated property-based testing problems across 40 real Python libraries.<n>Each problem injects one or more semantic bugs (365 in total, mean 3.65 per problem) designed so that default-strategy random inputs almost never trigger them.<n>Bug recall under the PBT-guided prompt ranges from 42.1% to 83.4% across models; under the open-ended baseline, from 31.4% to 76.7%.
  arXiv  Detail & Related papers  (2026-05-13T18:01:05Z)
• From Black Box to Glass Box: Cross-Model ASR Disagreement to Prioto Review in Ambient AI Scribe Documentation [43.148402136307716]
  Cross-model disagreement among heterogeneous ASR systems can act as a reference-free uncertainty signal.<n>We transcribed 50 publicly available medical audio clips with eight ASR systems spanning commercial APIs and open-source engines.<n>Low-agreement regions were enriched for content disagreements, with the content fraction increasing from 53.9% to 73.9% across quintiles of high-risk mass.
  arXiv  Detail & Related papers  (2026-03-02T13:02:13Z)
• When Prohibitions Become Permissions: Auditing Negation Sensitivity in Language Models [1.0671844383558033]
  Open-source models endorse prohibited actions 77% of the time under simple negation.<n>Financial scenarios prove twice as fragile as medical ones.<n>Findings point to a gap between what current alignment techniques achieve and what safe deployment requires.
  arXiv  Detail & Related papers  (2026-01-29T09:09:23Z)
• Prompt Injection Evaluations: Refusal Boundary Instability and Artifact-Dependent Compliance in GPT-4-Series Models [0.0]
  We evaluate two models, GPT-4.1 and GPT-4o, using 3,274 perturbation runs derived from refusal-inducing prompt injection attempts.<n>We find that artifact type is a stronger predictor of refusal failure than perturbation style.<n>We conclude that refusal behavior is a probabilistic, artifact-dependent boundary phenomenon rather than a stable binary property.
  arXiv  Detail & Related papers  (2026-01-25T17:14:33Z)
• Causal Understanding by LLMs: The Role of Uncertainty [43.87879175532034]
  Recent papers show LLMs achieve near-random accuracy in causal relation classification.<n>We investigate whether pretraining exposure to causal examples improves causal understanding.
  arXiv  Detail & Related papers  (2025-09-24T13:06:35Z)
• An Embarrassingly Simple Defense Against LLM Abliteration Attacks [47.347413305965006]
  A recent attack, termed abliteration, identifies and suppresses the single latent direction most responsible for refusal behavior.<n>We propose a defense that fundamentally alters how models express refusal.<n>Fine-tuning Llama-2-7B-Chat and Qwen2.5-Instruct yields models that maintain high refusal rates under abliteration.
  arXiv  Detail & Related papers  (2025-05-25T09:18:24Z)
• Exploring Response Uncertainty in MLLMs: An Empirical Evaluation under Misleading Scenarios [49.53589774730807]
  Multimodal large language models (MLLMs) have recently achieved state-of-the-art performance on tasks ranging from visual question answering to video understanding.<n>We reveal a response uncertainty phenomenon: twelve state-of-the-art open-source MLLMs overturn a previously correct answer in 65% of cases after receiving a single deceptive cue.
  arXiv  Detail & Related papers  (2024-11-05T01:11:28Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.