ArticleProceedings of the National Academy of Sciences of the United States of America2026
Persuading large language models to comply with objectionable requests.
Article in Proceedings of the National Academy of Sciences of the United States of America, 2026. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Cited by 1 paper.
What it found
Each row is one number read from the abstract, on the scale the paper reported it, with its interval. Left of the dashed line favours the treatment, right favours the comparator. Under each row is the sentence it came from. New to these charts? A ten-minute tutorial.
The abstract states no effect estimate the extractor could read, or names no intervention and outcome on the map, so this paper lights no cell and moves no belief. It is still indexed, cited and linked below.
The trial behind it
Trials whose registry record cites this paper, or whose number appears in the abstract. A trial that started after this paper was published is citing it as background, not reporting it.
Neither the registry nor the abstract names a trial number. If this is a trial report, that itself is worth knowing.
Who cites it
1 citing paper in PubMed.
- Persuading large language models to comply with objectionable requests.Proceedings of the National Academy of Sciences of the United States of America · 2026Article
Corrections and comments
PubMed lists nothing against this paper. Absence here is not a guarantee, only a check that was made.
Authors and funding
7 authors.
Funding
No grant is acknowledged in the PubMed record.
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.
Indexed as
Identifiers
What OpenQuestion holds
Registered trials
Read under generation 80e0d062 · epoch 390. Bibliography from PubMed, PubMed Central and OpenAlex; grants from NIH RePORTER; trial links from ClinicalTrials.gov; estimates, votes and beliefs from the OpenQuestion graph.