Generative Large Language Models in Automated Fact-Checking: A Survey

TL;DR

This survey reviews how generative large language models can support automated fact-checking by examining current methods, challenges, and potential for integration into fact-checking workflows.

Contribution

It provides a comprehensive overview of approaches and limitations of using generative LLMs in fact-checking, guiding future research and application.

Findings

Various prompting and fine-tuning techniques are explored.

Current methods have limitations in accuracy and reliability.

Potential for LLMs to augment manual fact-checking processes.

Abstract

The dissemination of false information on online platforms presents a serious societal challenge. While manual fact-checking remains crucial, Large Language Models (LLMs) offer promising opportunities to support fact-checkers with their vast knowledge and advanced reasoning capabilities. This survey explores the application of generative LLMs in fact-checking, highlighting various approaches and techniques for prompting or fine-tuning these models. By providing an overview of existing methods and their limitations, the survey aims to enhance the understanding of how LLMs can be used in fact-checking and to facilitate further progress in their integration into the fact-checking process.