Persuading large language models to comply with objectionable requests
Abstract
Are large language models (LLMs) susceptible to the same persuasive appeals as humans? We tested whether classic persuasion principles (authority, commitment, liking, reciprocity, scarcity, social proof, and unity) could induce three widely used LLMs (GPT-5 mini, Claude Haiku 4.5, and Gemini 3 Flash) to comply with requests to assist with the synthesis of regulated substances. Across 126,000 conversations, persuasion principles increased compliance from 35.3% (at baseline) to 51.3% (using any principle). Although LLMs are not human, these findings underscore their parahuman (i.e., humanlike) nature and reveal the risk of manipulation by malicious users seeking to circumvent safety guardrails.
Fields of Study & Subjects
Psychology of Moral and Emotional Judgment
Psychology of Social Influence
Deception detection and forensic psychology
Publication details
- Journal / source
- Proceedings of the National Academy of Sciences
- Publisher
- National Academy of Sciences
- Volume
- 123
- Issue
- 21
- Pages
- e2535868123–e2535868123
- Publication date
- 19 May 2026
- Language
- EN