The Earth is Flat because...: Investigating LLMs' Belief towards Misinformation via Persuasive Conversation
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2023
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866929367437803520 |
|---|---|
| author | Xu, Rongwu Lin, Brian S. Yang, Shujian Zhang, Tianqi Shi, Weiyan Zhang, Tianwei Fang, Zhixuan Xu, Wei Qiu, Han |
| author_facet | Xu, Rongwu Lin, Brian S. Yang, Shujian Zhang, Tianqi Shi, Weiyan Zhang, Tianwei Fang, Zhixuan Xu, Wei Qiu, Han |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2312_09085 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | The Earth is Flat because...: Investigating LLMs' Belief towards Misinformation via Persuasive Conversation Xu, Rongwu Lin, Brian S. Yang, Shujian Zhang, Tianqi Shi, Weiyan Zhang, Tianwei Fang, Zhixuan Xu, Wei Qiu, Han Computation and Language Artificial Intelligence Cryptography and Security Computers and Society 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. |
| title | The Earth is Flat because...: Investigating LLMs' Belief towards Misinformation via Persuasive Conversation |
| topic | Computation and Language Artificial Intelligence Cryptography and Security Computers and Society |
| url | https://arxiv.org/abs/2312.09085 |