Fact Verification
Fact verification, the automated process of assessing the truthfulness of claims, aims to combat the rapid spread of misinformation. Current research focuses on improving accuracy and explainability using various approaches, including large language models (LLMs) coupled with techniques like retrieval augmented generation (RAG), natural logic reasoning, and knowledge graph integration. These advancements are crucial for enhancing the reliability of online information and supporting fact-checking efforts across diverse domains and languages, impacting both scientific understanding and public discourse.
Papers
Augmenting the Veracity and Explanations of Complex Fact Checking via Iterative Self-Revision with LLMs
Xiaocheng Zhang, Xi Wang, Yifei Lu, Zhuangzhuang Ye, Jianing Wang, Mengjiao Bao, Peng Yan, Xiaohong Su
ChronoFact: Timeline-based Temporal Fact Verification
Anab Maulana Barik, Wynne Hsu, Mong Li Lee
Overview of Factify5WQA: Fact Verification through 5W Question-Answering
Suryavardan Suresh, Anku Rani, Parth Patwa, Aishwarya Reganti, Vinija Jain, Aman Chadha, Amitava Das, Amit Sheth, Asif Ekbal
Take It Easy: Label-Adaptive Self-Rationalization for Fact Verification and Explanation Generation
Jing Yang, Anderson Rocha