LLM Can be a Dangerous Persuader: Empirical Study of Persuasion Safety in Large Language Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Liu, Minqian, Xu, Zhiyang, Zhang, Xinyi, An, Heajun, Qadir, Sarvech, Zhang, Qi, Wisniewski, Pamela J., Cho, Jin-Hee, Lee, Sang Won, Jia, Ruoxi, Huang, Lifu
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913793205862400
author Liu, Minqian
Xu, Zhiyang
Zhang, Xinyi
An, Heajun
Qadir, Sarvech
Zhang, Qi
Wisniewski, Pamela J.
Cho, Jin-Hee
Lee, Sang Won
Jia, Ruoxi
Huang, Lifu
author_facet Liu, Minqian
Xu, Zhiyang
Zhang, Xinyi
An, Heajun
Qadir, Sarvech
Zhang, Qi
Wisniewski, Pamela J.
Cho, Jin-Hee
Lee, Sang Won
Jia, Ruoxi
Huang, Lifu
contents Recent advancements in Large Language Models (LLMs) have enabled them to approach human-level persuasion capabilities. However, such potential also raises concerns about the safety risks of LLM-driven persuasion, particularly their potential for unethical influence through manipulation, deception, exploitation of vulnerabilities, and many other harmful tactics. In this work, we present a systematic investigation of LLM persuasion safety through two critical aspects: (1) whether LLMs appropriately reject unethical persuasion tasks and avoid unethical strategies during execution, including cases where the initial persuasion goal appears ethically neutral, and (2) how influencing factors like personality traits and external pressures affect their behavior. To this end, we introduce PersuSafety, the first comprehensive framework for the assessment of persuasion safety which consists of three stages, i.e., persuasion scene creation, persuasive conversation simulation, and persuasion safety assessment. PersuSafety covers 6 diverse unethical persuasion topics and 15 common unethical strategies. Through extensive experiments across 8 widely used LLMs, we observe significant safety concerns in most LLMs, including failing to identify harmful persuasion tasks and leveraging various unethical persuasion strategies. Our study calls for more attention to improve safety alignment in progressive and goal-driven conversations such as persuasion.
format Preprint
id arxiv_https___arxiv_org_abs_2504_10430
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle LLM Can be a Dangerous Persuader: Empirical Study of Persuasion Safety in Large Language Models
Liu, Minqian
Xu, Zhiyang
Zhang, Xinyi
An, Heajun
Qadir, Sarvech
Zhang, Qi
Wisniewski, Pamela J.
Cho, Jin-Hee
Lee, Sang Won
Jia, Ruoxi
Huang, Lifu
Computation and Language
Artificial Intelligence
Human-Computer Interaction
Recent advancements in Large Language Models (LLMs) have enabled them to approach human-level persuasion capabilities. However, such potential also raises concerns about the safety risks of LLM-driven persuasion, particularly their potential for unethical influence through manipulation, deception, exploitation of vulnerabilities, and many other harmful tactics. In this work, we present a systematic investigation of LLM persuasion safety through two critical aspects: (1) whether LLMs appropriately reject unethical persuasion tasks and avoid unethical strategies during execution, including cases where the initial persuasion goal appears ethically neutral, and (2) how influencing factors like personality traits and external pressures affect their behavior. To this end, we introduce PersuSafety, the first comprehensive framework for the assessment of persuasion safety which consists of three stages, i.e., persuasion scene creation, persuasive conversation simulation, and persuasion safety assessment. PersuSafety covers 6 diverse unethical persuasion topics and 15 common unethical strategies. Through extensive experiments across 8 widely used LLMs, we observe significant safety concerns in most LLMs, including failing to identify harmful persuasion tasks and leveraging various unethical persuasion strategies. Our study calls for more attention to improve safety alignment in progressive and goal-driven conversations such as persuasion.
title LLM Can be a Dangerous Persuader: Empirical Study of Persuasion Safety in Large Language Models
topic Computation and Language
Artificial Intelligence
Human-Computer Interaction
url https://arxiv.org/abs/2504.10430