Denoising Rationalization for Multi-hop Fact Verification via Multi-granular Explainer

Jiasheng Si, Yingjie Zhu, Wenpeng Lu, Deyu Zhou


Abstract
The success of deep learning models on multi-hop fact verification has prompted researchers to understand the behavior behind their veracity. One feasible way is erasure search: obtaining the rationale by entirely removing a subset of input without compromising verification accuracy. Despite extensive exploration, current rationalization methods struggle to discern nuanced composition within the correlated evidence, which inevitably leads to noise rationalization in multi-hop scenarios. To address this issue, this paper explores the multi-granular rationale extraction method, aiming to realize the denoising rationalization for multi-hop fact verification. Specifically, given a pretrained veracity prediction model, two independent external explainers are introduced and trained collaboratively to enhance the discriminating ability by imposing varied constraints. Meanwhile, three key properties (Fidelity, Consistency, Salience) are introduced to regularize the denoising and faithful rationalization process. Additionally, a new Noiselessness metric is proposed to measure the purity of the rationales. Experimental results on three multi-hop fact verification datasets show that the proposed approach outperforms 12 baselines.
Anthology ID:
2024.findings-emnlp.736
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2024
Month:
November
Year:
2024
Address:
Miami, Florida, USA
Editors:
Yaser Al-Onaizan, Mohit Bansal, Yun-Nung Chen
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
12593–12608
Language:
URL:
https://aclanthology.org/2024.findings-emnlp.736
DOI:
Bibkey:
Cite (ACL):
Jiasheng Si, Yingjie Zhu, Wenpeng Lu, and Deyu Zhou. 2024. Denoising Rationalization for Multi-hop Fact Verification via Multi-granular Explainer. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 12593–12608, Miami, Florida, USA. Association for Computational Linguistics.
Cite (Informal):
Denoising Rationalization for Multi-hop Fact Verification via Multi-granular Explainer (Si et al., Findings 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.findings-emnlp.736.pdf