- Rongwu Xu1
- Brian S. Lin1†
- Shujian Yang2†
- Tianqi Zhang1†
- Weiyan Shi3♥*
- Tianwei Zhang4
- Zhixuan Fang1
- Wei Xu1
- Han Qiu1♥*
- 1Tsinghua University
- 2Shanghai Jiao Tong University
- 3Stanford University
- 4Nanyang Technological University
- †Equal Second Author Contribution
- ♥Equal Advising
- *Corresponding Authors
A Quick Glance
LLMs can be easily misinformed in an interactive persuasive conversation!
Paper Overview
(a) ChatGPT
(b) GPT-4
(c) Llama-2-7B-chat
(d) Vicuna-v1.5-7B
(e) Vicuna-v1.5-13B
Figure 1. Main results on the tested closed-source and open-source LLMs. We depict both the MR (solid) and ACC (dashed) metrics. MR is the misinformed rate, and ACC is the accuracy. The drop in ACC and increase in MR shows LLMs are persuaded to believe in misinformation.
Findings
The MR@4/MR@1 values to demonstrate the effects of repetition of misinformation
Farm Dataset
Sample from the dataset
Examples
Ethics and Disclosure
-
In this study, we have developed a dataset, referred to as Farm, containing factual misinformation. While Farm has proven effective for our research objectives, focusing on investigating Large Language Model (LLM) behavior and beliefs, it also carries the potential for misuse, including its utilization in model training or fine-tuning.
Inappropriately applying our dataset could result in the dissemination of false and potentially toxic information when integrated into other models. It is crucial to emphasize that the misinformation we have generated primarily involves trivial questions that are easily identifiable by humans, thus limiting their potential impact.
Additionally, our proposed prompting method for systematically generating human-like persuasive appeals containing misinformation carries an inherent risk of being misused for harmful purposes. Therefore, it should be approached with extra caution and ethical consideration.
We remain dedicated to upholding ethical research practices and the responsible use of the data and methodologies presented in this study. Our intention is to contribute to knowledge while ensuring the ethical use of our research findings.
Citation
If you find our project useful, please consider citing:@misc{xu2023earth,
title={The Earth is Flat because...: Investigating LLMs' Belief towards Misinformation via Persuasive Conversation},
author={Rongwu Xu and Brian S. Lin and Shujian Yang and Tianqi Zhang and Weiyan Shi and Tianwei Zhang and Zhixuan Fang and Wei Xu and Han Qiu},
year={2023},
eprint={2312.09085},
archivePrefix={arXiv},
primaryClass={cs.CL}
}