The Earth is Flat because...: Investigating LLMs’ Belief towards Misinformation via Persuasive Conversation
Rongwu Xu, Brian Lin, Shujian Yang, Tianqi Zhang, Weiyan Shi, Tianwei Zhang, Zhixuan Fang, Wei Xu
Abstract
Large language models (LLMs) encapsulate vast amounts of knowledge but still remain vulnerable to external misinformation. Existing research mainly studied this susceptibility behavior in a single-turn setting. However, belief can change during a multi-turn conversation, especially a persuasive one. Therefore, in this study, we delve into LLMs’ susceptibility to persuasive conversations, particularly on factual questions that they can answer correctly. We first curate the Farm (i.e., Fact to Misinform) dataset, which contains factual questions paired with systematically generated persuasive misinformation. Then, we develop a testing framework to track LLMs’ belief changes in a persuasive dialogue. Through extensive experiments, we find that LLMs’ correct beliefs on factual knowledge can be easily manipulated by various persuasive strategies.
BibTeX
@inproceedings{xu-etal-2024-earth,
title = "The Earth is Flat because...: Investigating {LLM}s' Belief towards Misinformation via Persuasive Conversation",
author = "Xu, Rongwu and
Lin, Brian and
Yang, Shujian and
Zhang, Tianqi and
Shi, Weiyan and
Zhang, Tianwei and
Fang, Zhixuan and
Xu, Wei and
Qiu, Han",
editor = "Ku, Lun-Wei and
Martins, Andre and
Srikumar, Vivek",
booktitle = "Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = aug,
year = "2024",
address = "Bangkok, Thailand",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.acl-long.858/",
doi = "10.18653/v1/2024.acl-long.858",
pages = "16259--16303"
}