Faithful Inference Chains Extraction for Fact Verification over Multi-view Heterogeneous Graph with Causal Intervention

Daoqi Chen, Yaxin Li, Zizhong Zhu, Xiaowang Zhang, Zhiyong Feng


Abstract
KG-based fact verification verifies the truthfulness of claims by retrieving evidence graphs from the knowledge graph. The *faithful inference chains*, which are precise relation paths between the mentioned entities and evidence entities, retrieve precise evidence graphs addressing poor performance and weak logic for fact verification. Due to the diversity of relation paths, existing methods rarely extract faithful inference chains. To alleviate these issues, we propose Multi-view Heterogeneous Graph with Causal Intervention (MHGCI): (i) We construct a Multi-view Heterogeneous Graph enhancing relation path extraction from the view of different mentioned entities. (ii) We propose a self-optimizing causal intervention model to generate assistant entities mitigating the out-of-distribution problem caused by counterfactual relations. (iii) We propose a grounding method to extract evidence graphs from the KG by faithful inference chains. Experiments on the public KG-based fact verification dataset FactKG demonstrate that our model provides precise evidence graphs and achieves state-of-the-art performance.
Anthology ID:
2025.coling-main.311
Volume:
Proceedings of the 31st International Conference on Computational Linguistics
Month:
January
Year:
2025
Address:
Abu Dhabi, UAE
Editors:
Owen Rambow, Leo Wanner, Marianna Apidianaki, Hend Al-Khalifa, Barbara Di Eugenio, Steven Schockaert
Venue:
COLING
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
4634–4645
Language:
URL:
https://aclanthology.org/2025.coling-main.311/
DOI:
Bibkey:
Cite (ACL):
Daoqi Chen, Yaxin Li, Zizhong Zhu, Xiaowang Zhang, and Zhiyong Feng. 2025. Faithful Inference Chains Extraction for Fact Verification over Multi-view Heterogeneous Graph with Causal Intervention. In Proceedings of the 31st International Conference on Computational Linguistics, pages 4634–4645, Abu Dhabi, UAE. Association for Computational Linguistics.
Cite (Informal):
Faithful Inference Chains Extraction for Fact Verification over Multi-view Heterogeneous Graph with Causal Intervention (Chen et al., COLING 2025)
Copy Citation:
PDF:
https://aclanthology.org/2025.coling-main.311.pdf