DDOR: Delta Debugging for Explainable Overrefusal Testing and Repair

• URL: http://arxiv.org/abs/2606.03601v1
• Date: Tue, 02 Jun 2026 13:07:12 GMT
• Title: DDOR: Delta Debugging for Explainable Overrefusal Testing and Repair
• Abstract summary: DDOR (Delta for OverRefusal) is a fully automated and explainable framework for overrefusal testing and repair.<n>It applies delta debug to localize minimal refusal-triggering fragments (mRTFs) that provide phrase-level, explainable evidence for why a refusal occurs.<n>It produces scalable and model-specific overrefusal test suites (approximately 1K cases per model)
• Score: 17.573294728864443
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: While safety alignment and guardrails help large language models (LLMs) avoid harmful outputs, they can also induce overrefusal, i.e., unwarranted rejection of benign queries that merely appear risky. We present DDOR (Delta Debugging for OverRefusal), a fully automated and explainable framework for overrefusal testing and repair in a black-box setting, where only model inputs and outputs are accessible and internal safety mechanisms remain opaque. DDOR applies delta debugging to localize minimal refusal-triggering fragments (mRTFs) that provide phrase-level, explainable evidence for why a refusal occurs. Conditioned on these mRTFs, DDOR generates diverse, context-rich prompts and performs multi-oracle validation to filter intrinsically unsafe or ambiguous cases, producing scalable and model-specific overrefusal test suites (approximately 1K cases per model). Beyond evaluation, we further leverage localized mRTFs to perform targeted prompt repair, substantially reducing overrefusal while preserving the original intent and maintaining safety on genuinely harmful inputs. Overall, DDOR offers a practical end-to-end solution to both evaluate and mitigate overrefusal, improving LLM usability without sacrificing safety.

Related papers

• REINS: Refusal-Enhanced Inhibitory Steering with Sparse Autoencoder Features [42.07883859906045]
  Sparse Autoencoders (SAEs) offer a lightweight inference-time path for adapting the behavior of large language models without retraining.<n>We observe that complex wrappers can still undermine existing SAE steering methods on harmful prompts.<n>We propose Refusal-Enhanced INhibitory Steering (REINS), which suppresses harmful continuation features and enhances safe refusal features.
  arXiv  Detail & Related papers  (2026-08-28T11:47:29Z)
• Guardian-as-an-Advisor: Advancing Next-Generation Guardian Models for Trustworthy LLMs [70.81495077853673]
  Hard-gated safety checkers often over-refuse and misalign with a vendor's model spec.<n>This work introduces Guardian-as-an-Advisor (GaaA), a soft-gating pipeline where a guardian predicts a binary risk label and prepends this advice to the original query for re-inference.<n>Overall, GaaA steers models to comply with the model spec, maintaining safety while reducing over-refusal.
  arXiv  Detail & Related papers  (2026-04-08T23:47:29Z)
• Beyond Over-Refusal: Scenario-Based Diagnostics and Post-Hoc Mitigation for Exaggerated Refusals in LLMs [10.896368527058714]
  Large language models (LLMs) frequently produce false refusals, declining benign requests that contain terms resembling unsafe queries.<n>We introduce two comprehensive benchmarks: the Exaggerated Safety Benchmark (XSB) for single-turn prompts, annotated with "Focus" keywords that identify refusal-inducing triggers, and the Multi-turn Scenario-based Exaggerated Safety Benchmark (MS-XSB)<n>Our benchmarks reveal that exaggerated refusals persist across diverse recent LLMs and are especially pronounced in complex, multi-turn scenarios.
  arXiv  Detail & Related papers  (2025-10-09T12:38:16Z)
• D-REX: A Benchmark for Detecting Deceptive Reasoning in Large Language Models [62.83226685925107]
  Deceptive Reasoning Exposure Suite (D-REX) is a novel dataset designed to evaluate the discrepancy between a model's internal reasoning process and its final output.<n>Each sample in D-REX contains the adversarial system prompt, an end-user's test query, the model's seemingly innocuous response, and, crucially, the model's internal chain-of-thought.<n>We demonstrate that D-REX presents a significant challenge for existing models and safety mechanisms.
  arXiv  Detail & Related papers  (2025-09-22T15:59:40Z)
• Just Enough Shifts: Mitigating Over-Refusal in Aligned Language Models with Targeted Representation Fine-Tuning [19.823784666021822]
  ACTOR minimizes over-refusals by leveraging internal activation patterns from diverse queries.<n>ACTOR precisely identifies and adjusts the activation components that trigger refusals, providing stronger control over the refusal mechanism.
  arXiv  Detail & Related papers  (2025-07-06T05:47:04Z)
• TrustLoRA: Low-Rank Adaptation for Failure Detection under Out-of-distribution Data [62.22804234013273]
  We propose a simple failure detection framework to unify and facilitate classification with rejection under both covariate and semantic shifts.<n>Our key insight is that by separating and consolidating failure-specific reliability knowledge with low-rank adapters, we can enhance the failure detection ability effectively and flexibly.
  arXiv  Detail & Related papers  (2025-04-20T09:20:55Z)
• Root Defence Strategies: Ensuring Safety of LLM at the Decoding Level [10.476222570886483]
  Large language models (LLMs) have demonstrated immense utility across various industries.<n>As LLMs advance, the risk of harmful outputs increases due to incorrect or malicious instruction prompts.<n>This paper examines the LLMs' capability to recognize harmful outputs, revealing and quantifying their proficiency in assessing the danger of previous tokens.
  arXiv  Detail & Related papers  (2024-10-09T12:09:30Z)
• Refuse Whenever You Feel Unsafe: Improving Safety in LLMs via Decoupled Refusal Training [67.30423823744506]
  We introduce a novel approach, Decoupled Refusal Training (DeRTa), designed to empower LLMs to refuse compliance to harmful prompts at any response position.<n>DeRTa incorporates two novel components: (1) Maximum Likelihood Estimation with Harmful Response Prefix, which trains models to recognize and avoid unsafe content by appending a segment of harmful response to the beginning of a safe response, and (2) Reinforced Transition Optimization (RTO), which equips models with the ability to transition from potential harm to safety refusal consistently throughout the harmful response sequence.
  arXiv  Detail & Related papers  (2024-07-12T09:36:33Z)
• Jailbreaking as a Reward Misspecification Problem [80.52431374743998]
  We propose a novel perspective that attributes this vulnerability to reward misspecification during the alignment process.<n>We introduce a metric ReGap to quantify the extent of reward misspecification and demonstrate its effectiveness.<n>We present ReMiss, a system for automated red teaming that generates adversarial prompts in a reward-misspecified space.
  arXiv  Detail & Related papers  (2024-06-20T15:12:27Z)
• On Prompt-Driven Safeguarding for Large Language Models [172.13943777203377]
  We find that in the representation space, the input queries are typically moved by safety prompts in a "higher-refusal" direction. Inspired by these findings, we propose a method for safety prompt optimization, namely DRO. Treating a safety prompt as continuous, trainable embeddings, DRO learns to move the queries' representations along or opposite the refusal direction, depending on their harmfulness.
  arXiv  Detail & Related papers  (2024-01-31T17:28:24Z)

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.