Japanese / English


論文の言語 英語
著者 David Selby, Kai Spriestersbach, Yuichiro Iwashita, Dennis Bappert, Archana Warrier, Sumantrak Mukherjee, Muhammad Nabeel Asim, Koichi Kise, Sebastian Vollmer
論文名 Quantitative knowledge retrieval from large language models
論文誌名 arXiv
書名 arXiv:2402.07770v1 [cs.IR]
ページ数 21 pages
年月 2024年2月
要約 Large language models (LLMs) have been extensively studied for their abilities to generate convincing natural language sequences, however their utility for quantitative information retrieval is less well understood. In this paper we explore the feasibility of LLMs as a mechanism for quantitative knowledge retrieval to aid data analysis tasks such as elicitation of prior distributions for Bayesian models and imputation of missing data. We present a prompt engineering framework, treating an LLM as an interface to a latent space of scientific literature, comparing responses in different contexts and domains against more established approaches. Implications and challenges of using LLMs as 'experts' are discussed.
URL https://arxiv.org/abs/2402.07770