Can LLMs Automate Fact-Checking Article Writing?
This work addresses a gap in automatic fact-checking by generating articles for broader dissemination, though it is incremental as it builds on existing pipelines.
The paper tackled the problem of automating the writing of fact-checking articles, which existing systems lack, by developing QRAFT, an LLM-based framework that mimics human workflows. The evaluation showed QRAFT outperforms previous text-generation methods but lags behind expert-written articles.
Automatic fact-checking aims to support professional fact-checkers by offering tools that can help speed up manual fact-checking. Yet, existing frameworks fail to address the key step of producing output suitable for broader dissemination to the general public: while human fact-checkers communicate their findings through fact-checking articles, automated systems typically produce little or no justification for their assessments. Here, we aim to bridge this gap. We argue for the need to extend the typical automatic fact-checking pipeline with automatic generation of full fact-checking articles. We first identify key desiderata for such articles through a series of interviews with experts from leading fact-checking organizations. We then develop QRAFT, an LLM-based agentic framework that mimics the writing workflow of human fact-checkers. Finally, we assess the practical usefulness of QRAFT through human evaluations with professional fact-checkers. Our evaluation shows that while QRAFT outperforms several previously proposed text-generation approaches, it lags considerably behind expert-written articles. We hope that our work will enable further research in this new and important direction.