Enregistré dans:
Détails bibliographiques
Auteurs principaux: Herserant, Tanguy, Guigue, Vincent
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:https://arxiv.org/abs/2505.02235
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866909601081851904
author Herserant, Tanguy
Guigue, Vincent
author_facet Herserant, Tanguy
Guigue, Vincent
contents Evaluating text summarization quality remains a critical challenge in Natural Language Processing. Current approaches face a trade-off between performance and interpretability. We present SEval-Ex, a framework that bridges this gap by decomposing summarization evaluation into atomic statements, enabling both high performance and explainability. SEval-Ex employs a two-stage pipeline: first extracting atomic statements from text source and summary using LLM, then a matching between generated statements. Unlike existing approaches that provide only summary-level scores, our method generates detailed evidence for its decisions through statement-level alignments. Experiments on the SummEval benchmark demonstrate that SEval-Ex achieves state-of-the-art performance with 0.580 correlation on consistency with human consistency judgments, surpassing GPT-4 based evaluators (0.521) while maintaining interpretability. Finally, our framework shows robustness against hallucination.
format Preprint
id arxiv_https___arxiv_org_abs_2505_02235
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle SEval-Ex: A Statement-Level Framework for Explainable Summarization Evaluation
Herserant, Tanguy
Guigue, Vincent
Computation and Language
Artificial Intelligence
Evaluating text summarization quality remains a critical challenge in Natural Language Processing. Current approaches face a trade-off between performance and interpretability. We present SEval-Ex, a framework that bridges this gap by decomposing summarization evaluation into atomic statements, enabling both high performance and explainability. SEval-Ex employs a two-stage pipeline: first extracting atomic statements from text source and summary using LLM, then a matching between generated statements. Unlike existing approaches that provide only summary-level scores, our method generates detailed evidence for its decisions through statement-level alignments. Experiments on the SummEval benchmark demonstrate that SEval-Ex achieves state-of-the-art performance with 0.580 correlation on consistency with human consistency judgments, surpassing GPT-4 based evaluators (0.521) while maintaining interpretability. Finally, our framework shows robustness against hallucination.
title SEval-Ex: A Statement-Level Framework for Explainable Summarization Evaluation
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2505.02235