Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Factuality of Large Language Models: A Survey

Yuxia Wang, Minghan Wang, Muhammad Arslan Manzoor, Fei Liu, Georgi Georgiev, Rocktim Jyoti Das, Preslav Nakov

TL;DR

This survey critically analyze existing work on evaluating and improving the factuality of large language models with the aim to identify the major challenges and their associated causes, pointing out to potential solutions for improving the factuality of LLMs, and analyzing the obstacles to automated factuality evaluation for open-ended text generation.

Abstract

Large language models (LLMs), especially when instruction-tuned for chat, have become part of our daily lives, freeing people from the process of searching, extracting, and integrating information from multiple sources by offering a straightforward answer to a variety of questions in a single place. Unfortunately, in many cases, LLM responses are factually incorrect, which limits their applicability in real-world scenarios. As a result, research on evaluating and improving the factuality of LLMs has attracted a lot of attention recently. In this survey, we critically analyze existing work with the aim to identify the major challenges and their associated causes, pointing out to potential solutions for improving the factuality of LLMs, and analyzing the obstacles to automated factuality evaluation for open-ended text generation. We further offer an outlook on where future research should go.

Factuality of Large Language Models: A Survey

TL;DR

This survey critically analyze existing work on evaluating and improving the factuality of large language models with the aim to identify the major challenges and their associated causes, pointing out to potential solutions for improving the factuality of LLMs, and analyzing the obstacles to automated factuality evaluation for open-ended text generation.

Abstract

Large language models (LLMs), especially when instruction-tuned for chat, have become part of our daily lives, freeing people from the process of searching, extracting, and integrating information from multiple sources by offering a straightforward answer to a variety of questions in a single place. Unfortunately, in many cases, LLM responses are factually incorrect, which limits their applicability in real-world scenarios. As a result, research on evaluating and improving the factuality of LLMs has attracted a lot of attention recently. In this survey, we critically analyze existing work with the aim to identify the major challenges and their associated causes, pointing out to potential solutions for improving the factuality of LLMs, and analyzing the obstacles to automated factuality evaluation for open-ended text generation. We further offer an outlook on where future research should go.
Paper Structure (26 sections, 1 figure, 2 tables)

This paper contains 26 sections, 1 figure, 2 tables.

Table of Contents

  1. Introduction
  2. Background
  3. Hallucination vs. Factuality
  4. Trustworthiness/Reliability vs. Factuality
  5. Evaluating Factuality
  6. Datasets and Metrics
  7. Other Metrics
  8. Improving Factuality
  9. Pre-training
  10. Tuning and RLXF
  11. Retrieval Augmentation
  12. Inference
  13. Decoding Strategy
  14. ICL and Self-reasoning
  15. Retrieval Augmentation
  16. ...and 11 more sections

Figures (1)

  • Figure 1: Fact-checker framework: claim processor, retriever, and verifier, with optional step of summarizing and explaining in gray.