Zero-shot Factual Consistency Evaluation Across Domains

Fuente: arXiv
Saved in:
Bibliographic Details
Main Author: Agarwal, Raunak
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917744082944000
author Agarwal, Raunak
author_facet Agarwal, Raunak
contents This work addresses the challenge of factual consistency in text generation systems. We unify the tasks of Natural Language Inference, Summarization Evaluation, Factuality Verification and Factual Consistency Evaluation to train models capable of evaluating the factual consistency of source-target pairs across diverse domains. We rigorously evaluate these against eight baselines on a comprehensive benchmark suite comprising 22 datasets that span various tasks, domains, and document lengths. Results demonstrate that our method achieves state-of-the-art performance on this heterogeneous benchmark while addressing efficiency concerns and attaining cross-domain generalization.
format Preprint
id arxiv_https___arxiv_org_abs_2408_04114
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Zero-shot Factual Consistency Evaluation Across Domains
Agarwal, Raunak
Computation and Language
Machine Learning
This work addresses the challenge of factual consistency in text generation systems. We unify the tasks of Natural Language Inference, Summarization Evaluation, Factuality Verification and Factual Consistency Evaluation to train models capable of evaluating the factual consistency of source-target pairs across diverse domains. We rigorously evaluate these against eight baselines on a comprehensive benchmark suite comprising 22 datasets that span various tasks, domains, and document lengths. Results demonstrate that our method achieves state-of-the-art performance on this heterogeneous benchmark while addressing efficiency concerns and attaining cross-domain generalization.
title Zero-shot Factual Consistency Evaluation Across Domains
topic Computation and Language
Machine Learning
url https://arxiv.org/abs/2408.04114