Lune

CHI2026Top-tier venue

"Can LLMs Persuade Humans with Deception?": From a Deceptive Strategy Taxonomy to a Large-Scale Empirical Study

Haein Yeo, Seungwan Jin, Taehyung Noh, Yejin Shin, Sangyeon Kang, Sangwoo Heo, Jiwon Chung, Hwarim Hyun, Kyungsik Han

Abstract

Beyond hallucinations, Large Language Models (LLMs) can craft deceptive arguments that erode users’ critical thinking, posing a significant yet underexamined societal risk. To address this gap, we develop a taxonomy of eight deceptive persuasion strategies by integrating top-down rhetorical theory with a bottom-up analysis of 3,360 AI-generated messages by four LLM families and examining their effects on user perceptions. Through a large-scale user study (N=602) complemented by a think-aloud protocol, we found that participants were vulnerable to Information Manipulation and Uncertainty Exploitation, especially when a message contradicted their prior beliefs. Vulnerability was significantly higher for participants with low cognitive reflection, low topic knowledge, and low topic involvement. Qualitative analyses further revealed that participants were persuaded by the plausibility of an overall narrative even when they distrusted specific details, interpreting deceptive outputs as logically framed information that broadens perspective. We discuss critical implications of these findings for the design of trustworthy AI systems, adaptive user interfaces, and targeted literacy education.

Ask Lune

Know where this paper stands in minutes, not an afternoon.

Lune can read the top-tier papers that cite it and the ones closest to it, and tells you what it claims, what came after and where it falls short, each point cited to the paper it comes from. No skimming, no AI slop.

Questions to start from

Lune can draw on

its abstract · related work

Get the answer

Free to start. No credit card required.

Related papers

  1. Deceptive Explanations by Large Language Models Lead People to Change their Beliefs About Misinformation More Often than Honest ExplanationsValdemar Danry, Pat Pataranutaporn, Matthew Groh, Ziv EpsteinCHI 2025 · 32 citations
  2. A Generalizable Rhetorical Strategy Annotation Model Using LLM-based Debate Simulation and LabellingShiyu Ji, Farnoosh Hashemi, Joice Chen, Juanwen Pan et al.EMNLP Findings 2025
  3. Language Models can Subtly Deceive Without Lying: A Case Study on Strategic Phrasing in LegislationAtharvan Dogra, Krishna Pillutla, Ameet Deshpande, Ananya B. Sai et al.ACL 2025
  4. "I understand your perspective": LLM Persuasion through the Lens of Communicative Action TheoryEsra Dönmez, Agnieszka FalenskaACL Findings 2025 · 1 citation
  5. Working With AI to Persuade: Examining a Large Language Model's Ability to Generate Pro-Vaccination MessagesElise Karinshak, Sunny Xun Liu, Joon Sung Park, Jeffrey T. HancockCSCW 2023 · 163 citations
Dusk over the sea between two cliffs drawn in fine vertical lines