JustiLM: Few-shot Justification Generation for Explainable Fact-Checking of Real-world Claims
Transactions of the Association for Computational Linguistics · 05.04.2024 · 12 · 334-354
DOI: 10.1162/tacl_a_00649 ↗Kurz gefasst
Fachartikel in der Zeitschrift Transactions of the Association for Computational Linguistics, online erschienen am 05.04.2024. Verfasst von Fengzhu Zeng und 1 weiteren Autor:innen. Die Arbeit wurde bisher 21-mal zitiert (Crossref) und nennt 82 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Justification is an explanation that supports the veracity assigned to a claim in fact-checking. However, the task of justification generation has been previously oversimplified as summarization of a fact-check article authored by fact-checkers. Therefore, we propose a realistic approach to generate justification based on retrieved evidence. We present a new benchmark dataset called ExClaim (for Explainable fact-checking of real-world Claims), and introduce JustiLM, a novel few-shot Justification generation based on retrieval-augmented Language Model by using fact-check articles as an auxiliary resource during training only. Experiments show that JustiLM achieves promising performance in justification generation compared to strong baselines, and can also enhance veracity classification with a straightforward extension.1 Code and dataset are released at https://github.com/znhy1024/JustiLM.
Zitieren
APA
Zeng, F., & Gao, W. (2024). JustiLM: Few-shot Justification Generation for Explainable Fact-Checking of Real-world Claims. Transactions of the Association for Computational Linguistics, 12, 334-354. https://doi.org/10.1162/tacl_a_00649
Vancouver
Zeng F, Gao W. JustiLM: Few-shot Justification Generation for Explainable Fact-Checking of Real-world Claims. Transactions of the Association for Computational Linguistics. 2024;12:334-354. doi:10.1162/tacl_a_00649
BibTeX
@article{Zeng2024,
author = {Zeng, Fengzhu and Gao, Wei},
title = {JustiLM: Few-shot Justification Generation for Explainable Fact-Checking of Real-world Claims},
journal = {Transactions of the Association for Computational Linguistics},
year = {2024},
volume = {12},
pages = {334--354},
doi = {10.1162/tacl_a_00649}
}
EUVIMED