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

Computer Science > Artificial Intelligence [Submitted on 3 Apr 2026] Blind Refusal: Language Models Refuse to Help Users Evade Unjust, Absurd, and Illegitimate Rules Cameron Pattison, Lorenzo Manuali, Seth Lazar 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. Comments: 9 pages body text, 38 pages total, 4 figures Subjects: Artificial Intelligence (cs.AI) Cite as: arXiv:2604.06233 [cs.AI]   (or arXiv:2604.06233v1 [cs.AI] for this version)   https://doi.org/10.48550/arXiv.2604.06233 Focus to learn more Submission history From: Cameron Pattison [view email] [v1] Fri, 3 Apr 2026 13:53:23 UTC (399 KB) Access Paper: HTML (experimental) view license Current browse context: cs.AI < prev   |   next > new | recent | 2026-04 Change to browse by: cs References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)