Trucidator: Document-level Event Factuality Identification via Hallucination Enhancement and Cross-Document Inference

Zihao Zhang, Zhong Qian, Xiaoxu Zhu, Peifeng Li, Qiaoming Zhu


Abstract
Document-level event factuality identification (DEFI) assesses the veracity degree to which an event mentioned in a document has happened, which is crucial for many natural language processing tasks. Previous work assesses evet factuality by solely relying on the semantic information within a single document, which fails to identify hard cases where the document itself is hallucinative or counterfactual. There is also a pressing need for more suitable data of this kind. To tackle these issues, we construct Factualusion, a novel corpus with hallucination features that can be used not only for DEFI but can also be applied for hallucination evaluation for large language models. We further propose Trucidator, a graph-based framework that constructs intra-document and cross-document graphs and employs a multi-task learning paradigm to acquire more robust node embeddings, leveraging cross-document inference for more accurate identification. Experiments show that our proposed framework outperformed several baselines, demonstrating the effectiveness of our method.
Anthology ID:
2025.coling-main.139
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:
2038–2048
Language:
URL:
https://aclanthology.org/2025.coling-main.139/
DOI:
Bibkey:
Cite (ACL):
Zihao Zhang, Zhong Qian, Xiaoxu Zhu, Peifeng Li, and Qiaoming Zhu. 2025. Trucidator: Document-level Event Factuality Identification via Hallucination Enhancement and Cross-Document Inference. In Proceedings of the 31st International Conference on Computational Linguistics, pages 2038–2048, Abu Dhabi, UAE. Association for Computational Linguistics.
Cite (Informal):
Trucidator: Document-level Event Factuality Identification via Hallucination Enhancement and Cross-Document Inference (Zhang et al., COLING 2025)
Copy Citation:
PDF:
https://aclanthology.org/2025.coling-main.139.pdf