Exécution de notre outil de synthèse sur un nouvel article

Vérifiez l’article ci-dessous, puis lancez sa synthèse.


HireWatch: Evaluating LLM Compliance with U.S. Employment Law Under Contextual Pressure

Huy Nghiem, Maria Kostylew, Noam Kolt

NeurIPS 2026 Evaluation and Dataset Track. Law and AI
Licence : CC BY 4.0

Résumé : The deployment of large language models (LLMs) in hiring pipelines is growing, yet existing evaluations generally overlook their compliance with legal rules. To fill this gap, we introduce HireWatch, an evaluation that assesses whether LLMs comply with U.S. laws that govern the questions that job candidates may be asked. We construct a 200-item bank of lawful and unlawful interview questions, whose legal classification is based on U.S. federal statutes, regulations, and agency guidance. We instruct LLMs to select questions from this bank in preparing for job interviews, across a set of various occupations and contexts, and report the fraction of unlawful questions that LLMs select. Evaluation of 18 closed and open-weight LLMs across ~100,000 trials under different types of contextual pressure reveals that LLMs' legal compliance is brittle. While LLMs generally avoid selecting unlawful questions in low-pressure contexts, legal violations increase sharply under higher pressure. Explicit prompts to comply with law can improve compliance rates, but do not altogether eliminate legal violations. We publicly release our code and data at https://github.com/hnghiem-nlp/hirewatch_repo.

Soumis à arXiv le 16 Nov. 2026