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

TL;DR

This survey explores the application of generative LLMs in fact-checking, highlighting various approaches and techniques for prompting or fine-tuning these models.

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.

Figures (2)

• Figure 1: A taxonomy of methods for integrating generative LLMs in fact-checking, illustrating examples of model inputs and outputs. The methods employed with generative LLMs are classified based on the output type.
• Figure 2: The occurrence frequency of the models in the reviewed papers. We only present models used in more than five papers.