[Xiong, Kai] Harbin Inst Technol, Harbin, Peoples R China.
[Cui, Long; Liu, Yongbin; He, Yidong] Univ South China, Guangzhou, Peoples R China.
通讯机构：
[Cao, YX ] S
Singapore Management Univ, Singapore, Singapore.
语种：
英文
期刊：
PROCEEDINGS OF THE 62ND ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, VOL 1: LONG PAPERS
年：
2024
页码：
4221-4246
会议名称：
62nd Annual Meeting of the Association-for-Computational-Linguistics (ACL) / Student Research Workshop (SRW)
会议时间：
AUG 11-16, 2024
会议地点：
Bangkok, THAILAND
会议主办单位：
[Ying, Jiahao;Cao, Yixin] Singapore Management Univ, Singapore, Singapore.^[Xiong, Kai] Harbin Inst Technol, Harbin, Peoples R China.^[He, Yidong;Cui, Long;Liu, Yongbin] Univ South China, Guangzhou, Peoples R China.
主编：
Ku, LW Martins, A Srikumar, V
出版地：
209 N EIGHTH STREET, STROUDSBURG, PA 18360 USA
出版者：
ASSOC COMPUTATIONAL LINGUISTICS-ACL
ISBN：
979-8-89176-094-3
基金类别：
Lee Kong Chian Fellowship fund - Singapore Management University; Google South Asia & Southeast Asia Research Awards by Google Asia Pacific Pte. Ltd.
机构署名：
本校为其他机构
摘要：
This study investigates the behaviors of Large Language Models (LLMs) when faced with conflicting prompts versus their internal memory. This will not only help to understand LLMs' decision mechanism but also benefit real-world applications, such as retrieval-augmented generation (RAG). Drawing on cognitive theory, we target the first scenario of decision-making styles where there is no superiority in the conflict and categorize LLMs' preference into dependent, intuitive, and rational/irrational styles. Another scenario of factual robustness considers the correctness of prompt and memory in kno...
