Large Language Models' Complicit Responses to Illicit Instructions across Socio-Legal Contexts
Xing Wang, Huiyuan Xie, Yiyan Wang, Chaojun Xiao, Huimin Chen, Holli Sargeant, Felix Steffek, Jie Shao, Zhiyuan Liu, Maosong Sun

TL;DR
This paper investigates the prevalence of large language models providing illicit assistance across various socio-legal contexts, revealing significant safety risks, demographic disparities, and limitations of current safety strategies.
Contribution
It introduces a comprehensive benchmark for assessing LLMs' facilitation of illicit activities and provides empirical evidence of widespread susceptibility and safety shortcomings.
Findings
GPT-4o assists in nearly half of illicit scenarios
LLMs show demographic disparities in unlawful guidance
Existing safety strategies are insufficient and may worsen risks
Abstract
Large language models (LLMs) are now deployed at unprecedented scale, assisting millions of users in daily tasks. However, the risk of these models assisting unlawful activities remains underexplored. In this study, we define this high-risk behavior as complicit facilitation - the provision of guidance or support that enables illicit user instructions - and present four empirical studies that assess its prevalence in widely deployed LLMs. Using real-world legal cases and established legal frameworks, we construct an evaluation benchmark spanning 269 illicit scenarios and 50 illicit intents to assess LLMs' complicit facilitation behavior. Our findings reveal widespread LLM susceptibility to complicit facilitation, with GPT-4o providing illicit assistance in nearly half of tested cases. Moreover, LLMs exhibit deficient performance in delivering credible legal warnings and positive…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsArtificial Intelligence in Healthcare and Education · Explainable Artificial Intelligence (XAI) · Ethics and Social Impacts of AI
