Generative Large Language Models in Automated Fact-Checking: A Survey
It tackles the problem of misinformation for fact-checkers and researchers by surveying existing LLM-based approaches, but it is incremental as it reviews rather than introduces new methods.
This survey explores the application of generative large language models (LLMs) in automated fact-checking to address the societal challenge of false information online, providing an overview of methods and limitations to enhance understanding and facilitate integration into fact-checking processes.
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.