FinGrAct: A Framework for FINe-GRrained Evaluation of ACTionability in Explainable Automatic Fact-Checking

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Eldifrawi, Islam, Wang, Shengrui, Trabelsi, Amine
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912313718603776
author Eldifrawi, Islam
Wang, Shengrui
Trabelsi, Amine
author_facet Eldifrawi, Islam
Wang, Shengrui
Trabelsi, Amine
contents The field of explainable Automatic Fact-Checking (AFC) aims to enhance the transparency and trustworthiness of automated fact-verification systems by providing clear and comprehensible explanations. However, the effectiveness of these explanations depends on their actionability --their ability to empower users to make informed decisions and mitigate misinformation. Despite actionability being a critical property of high-quality explanations, no prior research has proposed a dedicated method to evaluate it. This paper introduces FinGrAct, a fine-grained evaluation framework that can access the web, and it is designed to assess actionability in AFC explanations through well-defined criteria and an evaluation dataset. FinGrAct surpasses state-of-the-art (SOTA) evaluators, achieving the highest Pearson and Kendall correlation with human judgments while demonstrating the lowest ego-centric bias, making it a more robust evaluation approach for actionability evaluation in AFC.
format Preprint
id arxiv_https___arxiv_org_abs_2504_05229
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle FinGrAct: A Framework for FINe-GRrained Evaluation of ACTionability in Explainable Automatic Fact-Checking
Eldifrawi, Islam
Wang, Shengrui
Trabelsi, Amine
Artificial Intelligence
The field of explainable Automatic Fact-Checking (AFC) aims to enhance the transparency and trustworthiness of automated fact-verification systems by providing clear and comprehensible explanations. However, the effectiveness of these explanations depends on their actionability --their ability to empower users to make informed decisions and mitigate misinformation. Despite actionability being a critical property of high-quality explanations, no prior research has proposed a dedicated method to evaluate it. This paper introduces FinGrAct, a fine-grained evaluation framework that can access the web, and it is designed to assess actionability in AFC explanations through well-defined criteria and an evaluation dataset. FinGrAct surpasses state-of-the-art (SOTA) evaluators, achieving the highest Pearson and Kendall correlation with human judgments while demonstrating the lowest ego-centric bias, making it a more robust evaluation approach for actionability evaluation in AFC.
title FinGrAct: A Framework for FINe-GRrained Evaluation of ACTionability in Explainable Automatic Fact-Checking
topic Artificial Intelligence
url https://arxiv.org/abs/2504.05229