With the growing complexity of fact verification tasks, the concern with “thoughtful” reasoning capabilities is increasing. However, recent fact verification benchmarks mainly focus on checking a narrow scope of semantic factoids within claims and lack an explicit logical reasoning process. In this paper, we introduce CHECKWHY, a challenging dataset tailored to a novel causal fact verification task: checking the truthfulness of the causal relation within claims through rigorous reasoning steps. CHECKWHY consists of over 19K “why” claim-evidence- argument structure triplets with supports, refutes, and not enough info labels. Each argument structure is composed of connected evidence, representing the reasoning process that begins with foundational evidence and progresses toward claim establishment. Through extensive experiments on state-of-the-art models, we validate the importance of incorporating the argument structure for causal fact verification. Moreover, the automated and human evaluation of argument structure generation reveals the difficulty in producing satisfying argument structure by fine-tuned models or Chain-of-Thought prompted LLMs, leaving considerable room for future improvements.
SAC Award: Sentiment Analysis, Stylistic Analysis, and Argument Mining
Bibkey:
Cite (ACL):
Jiasheng Si, Yibo Zhao, Yingjie Zhu, Haiyang Zhu, Wenpeng Lu, and Deyu Zhou. 2024.CHECKWHY: Causal Fact Verification via Argument Structure. InProceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 15636–15659, Bangkok, Thailand. Association for Computational Linguistics.
@inproceedings{si-etal-2024-checkwhy, title = "{CHECKWHY}: Causal Fact Verification via Argument Structure", author = "Si, Jiasheng and Zhao, Yibo and Zhu, Yingjie and Zhu, Haiyang and Lu, Wenpeng and Zhou, Deyu", editor = "Ku, Lun-Wei and Martins, Andre and Srikumar, Vivek", booktitle = "Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)", month = aug, year = "2024", address = "Bangkok, Thailand", publisher = "Association for Computational Linguistics", url = "https://aclanthology.org/2024.acl-long.835/", doi = "10.18653/v1/2024.acl-long.835", pages = "15636--15659", abstract = "With the growing complexity of fact verification tasks, the concern with {\textquotedblleft}thoughtful{\textquotedblright} reasoning capabilities is increasing. However, recent fact verification benchmarks mainly focus on checking a narrow scope of semantic factoids within claims and lack an explicit logical reasoning process. In this paper, we introduce CHECKWHY, a challenging dataset tailored to a novel causal fact verification task: checking the truthfulness of the causal relation within claims through rigorous reasoning steps. CHECKWHY consists of over 19K {\textquotedblleft}why{\textquotedblright} claim-evidence- argument structure triplets with supports, refutes, and not enough info labels. Each argument structure is composed of connected evidence, representing the reasoning process that begins with foundational evidence and progresses toward claim establishment. Through extensive experiments on state-of-the-art models, we validate the importance of incorporating the argument structure for causal fact verification. Moreover, the automated and human evaluation of argument structure generation reveals the difficulty in producing satisfying argument structure by fine-tuned models or Chain-of-Thought prompted LLMs, leaving considerable room for future improvements."}
%0 Conference Proceedings%T CHECKWHY: Causal Fact Verification via Argument Structure%A Si, Jiasheng%A Zhao, Yibo%A Zhu, Yingjie%A Zhu, Haiyang%A Lu, Wenpeng%A Zhou, Deyu%Y Ku, Lun-Wei%Y Martins, Andre%Y Srikumar, Vivek%S Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)%D 2024%8 August%I Association for Computational Linguistics%C Bangkok, Thailand%F si-etal-2024-checkwhy%X With the growing complexity of fact verification tasks, the concern with “thoughtful” reasoning capabilities is increasing. However, recent fact verification benchmarks mainly focus on checking a narrow scope of semantic factoids within claims and lack an explicit logical reasoning process. In this paper, we introduce CHECKWHY, a challenging dataset tailored to a novel causal fact verification task: checking the truthfulness of the causal relation within claims through rigorous reasoning steps. CHECKWHY consists of over 19K “why” claim-evidence- argument structure triplets with supports, refutes, and not enough info labels. Each argument structure is composed of connected evidence, representing the reasoning process that begins with foundational evidence and progresses toward claim establishment. Through extensive experiments on state-of-the-art models, we validate the importance of incorporating the argument structure for causal fact verification. Moreover, the automated and human evaluation of argument structure generation reveals the difficulty in producing satisfying argument structure by fine-tuned models or Chain-of-Thought prompted LLMs, leaving considerable room for future improvements.%R 10.18653/v1/2024.acl-long.835%U https://aclanthology.org/2024.acl-long.835/%U https://doi.org/10.18653/v1/2024.acl-long.835%P 15636-15659
Jiasheng Si, Yibo Zhao, Yingjie Zhu, Haiyang Zhu, Wenpeng Lu, and Deyu Zhou. 2024.CHECKWHY: Causal Fact Verification via Argument Structure. InProceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 15636–15659, Bangkok, Thailand. Association for Computational Linguistics.