Publication Type

Conference Proceeding Article

Version

publishedVersion

Publication Date

7-2023

Abstract

Few-shot or zero-shot fact verification only relies on a few or no labeled training examples. In this paper, we propose a novel method called ProToCo, to Prompt pre-trained language models (PLMs) To be Consistent, for improving the factuality assessment capability of PLMs in the few-shot and zero-shot settings. Given a claim-evidence pair, ProToCo generates multiple variants of the claim with different relations and frames a simple consistency mechanism as constraints for making compatible predictions across these variants. We update PLMs by using parameter-efficient fine-tuning (PEFT), leading to more accurate predictions in few-shot and zero-shot fact verification tasks. Our experiments on three public verification datasets show that ProToCo significantly outperforms state-of-the-art few-shot fact verification baselines. With a small number of unlabeled instances, ProToCo also outperforms the strong zero-shot learner T0 on zero-shot verification. Compared to large PLMs using in-context learning (ICL) method, ProToCo outperforms OPT-30B and the Self-Consistency-enabled OPT-6.7B model in both few- and zero-shot settings.

Keywords

few-shot fact verification, zero-shot fact verification, ProToCo, Prompt pre-trained language models, factuality assessment, claim-evidence pair, consistency mechanism, variants, predictions, parameter-efficient fine-tuning (PEFT), accurate predictions, public verification datasets, zero-shot learner, in-context learning (ICL), OPT-30B, Self-Consistency-enabled OPT-6.7B model

Discipline

Computer Sciences

Research Areas

Data Science and Engineering

Publication

Findings of the Association for Computational Linguistics: ACL 2023

First Page

4555

Last Page

4569

Identifier

10.18653/v1/2023.findings-acl.278

Publisher

Association for Computational Linguistics

City or Country

USA

Copyright Owner and License

Authors

Additional URL

https://doi.org/10.18653/v1/2023.findings-acl.278

Share

COinS