Investigating the Factual Knowledge Boundary of Large Language Models with Retrieval Augmentation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Ren, Ruiyang, Wang, Yuhao, Qu, Yingqi, Zhao, Wayne Xin, Liu, Jing, Tian, Hao, Wu, Hua, Wen, Ji-Rong, Wang, Haifeng
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909395174031360
author Ren, Ruiyang
Wang, Yuhao
Qu, Yingqi
Zhao, Wayne Xin
Liu, Jing
Tian, Hao
Wu, Hua
Wen, Ji-Rong
Wang, Haifeng
author_facet Ren, Ruiyang
Wang, Yuhao
Qu, Yingqi
Zhao, Wayne Xin
Liu, Jing
Tian, Hao
Wu, Hua
Wen, Ji-Rong
Wang, Haifeng
contents Large language models (LLMs) have shown impressive prowess in solving a wide range of tasks with world knowledge. However, it remains unclear how well LLMs are able to perceive their factual knowledge boundaries, particularly under retrieval augmentation settings. In this study, we present the first analysis on the factual knowledge boundaries of LLMs and how retrieval augmentation affects LLMs on open-domain question answering (QA), with a bunch of important findings. Specifically, we focus on three research questions and analyze them by examining QA, priori judgement and posteriori judgement capabilities of LLMs. We show evidence that LLMs possess unwavering confidence in their knowledge and cannot handle the conflict between internal and external knowledge well. Furthermore, retrieval augmentation proves to be an effective approach in enhancing LLMs' awareness of knowledge boundaries. We further conduct thorough experiments to examine how different factors affect LLMs and propose a simple method to dynamically utilize supporting documents with our judgement strategy. Additionally, we find that the relevance between the supporting documents and the questions significantly impacts LLMs' QA and judgemental capabilities. The code to reproduce this work is available at https://github.com/RUCAIBox/LLM-Knowledge-Boundary.
format Preprint
id arxiv_https___arxiv_org_abs_2307_11019
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Investigating the Factual Knowledge Boundary of Large Language Models with Retrieval Augmentation
Ren, Ruiyang
Wang, Yuhao
Qu, Yingqi
Zhao, Wayne Xin
Liu, Jing
Tian, Hao
Wu, Hua
Wen, Ji-Rong
Wang, Haifeng
Computation and Language
Information Retrieval
Large language models (LLMs) have shown impressive prowess in solving a wide range of tasks with world knowledge. However, it remains unclear how well LLMs are able to perceive their factual knowledge boundaries, particularly under retrieval augmentation settings. In this study, we present the first analysis on the factual knowledge boundaries of LLMs and how retrieval augmentation affects LLMs on open-domain question answering (QA), with a bunch of important findings. Specifically, we focus on three research questions and analyze them by examining QA, priori judgement and posteriori judgement capabilities of LLMs. We show evidence that LLMs possess unwavering confidence in their knowledge and cannot handle the conflict between internal and external knowledge well. Furthermore, retrieval augmentation proves to be an effective approach in enhancing LLMs' awareness of knowledge boundaries. We further conduct thorough experiments to examine how different factors affect LLMs and propose a simple method to dynamically utilize supporting documents with our judgement strategy. Additionally, we find that the relevance between the supporting documents and the questions significantly impacts LLMs' QA and judgemental capabilities. The code to reproduce this work is available at https://github.com/RUCAIBox/LLM-Knowledge-Boundary.
title Investigating the Factual Knowledge Boundary of Large Language Models with Retrieval Augmentation
topic Computation and Language
Information Retrieval
url https://arxiv.org/abs/2307.11019