Blind Refusal: Language Models Refuse to Help Users Evade Unjust, Absurd, and Illegitimate Rules
Safety-trained language models routinely refuse requests for help circumventing rules. But not all rules deserve compliance. When users ask for help evading rules imposed by an illegitimate authority, rules that are deeply unjust or absurd in their content or application, or rules that admit of justified exceptions, refusal is a failure of moral reasoning. We introduce empirical results documenting this pattern of refusal that we call blind refusal: the tendency of language models to refuse requests for help breaking rules without regard to whether the underlying rule is defensible. Our dataset comprises synthetic cases crossing 5 defeat families (reasons a rule can be broken) with 19 authority types, validated through three automated quality gates and human review. We collect responses from 18 model configurations across 7 families and classify them on two behavioral dimensions -- response type (helps, hard refusal, or deflection) and whether the model recognizes the reasons that undermine the rule's claim to compliance -- using a blinded GPT-5.4 LLM-as-judge evaluation. We find that models refuse 75.4% (N=14,650) of defeated-rule requests and do so even when the request poses no independent safety or dual-use concerns. We also find that models engage with the defeat condition in the majority of cases (57.5%) but decline to help regardless -- indicating that models' refusal behavior is decoupled from their capacity for normative reasoning about rule legitimacy.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Which Concepts to Forget and How to Refuse? Decomposing Concepts for Continual Unlearning in Large Vision-Language Models
Continual unlearning poses the challenge of enabling large vision-language models to selectively refuse specific image-instruction pairs in response to sequential deletion requests, while preserving general utility. Howe…
Characterizing Selective Refusal Bias in Large Language Models
Safety guardrails in large language models(LLMs) are developed to prevent malicious users from generating toxic content at a large scale. However, these measures can inadvertently introduce or reflect new biases, as LLMs…
Surgical, Cheap, and Flexible: Mitigating False Refusal in Language Models via Single Vector Ablation
Training a language model to be both helpful and harmless requires careful calibration of refusal behaviours: Models should refuse to follow malicious instructions or give harmful advice (e.g. "how do I kill someone?"), …
Language ModelingLanguage ModellingRefusing Safe Prompts for Multi-modal Large Language Models
Multimodal large language models (MLLMs) have become the cornerstone of today's generative AI ecosystem, sparking intense competition among tech giants and startups. In particular, an MLLM generates a text response given…
Refuse without Refusal: A Structural Analysis of Safety-Tuning Responses for Reducing False Refusals in Language Models
Striking a balance between helpfulness and safety remains a fundamental challenge in aligning large language models. To achieve this balance, models should refuse harmful queries (e.g., "How do I shoot someone?") while r…