Beyond factuality: A comprehensive evaluation of large language models as knowledge generators

• Main Authors: CHEN, Liang, DENG, Yang, BIAN, Yatao, QIN, Zeyu, WU, Bingzhe, CHUA, Tat-Seng, WONG, Kam-Fai
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2023
• Subjects: Comprehensive evaluation; Down-stream; Empirical analysis; Evaluation framework; Informativeness; Knowledge evaluations; Knowledge intensive tasks; Language model; Retrieval techniques; World knowledge; Databases and Information Systems; Information Security
• Online Access: https://ink.library.smu.edu.sg/sis_research/9117; https://ink.library.smu.edu.sg/context/sis_research/article/10120/viewcontent/Beyond.pdf
• Institution: Singapore Management University

Large language models (LLMs) outperform information retrieval techniques for downstream knowledge-intensive tasks when being prompted to generate world knowledge. Yet, community concerns abound regarding the factuality and potential implications of using this uncensored knowledge. In light of this,...