ZeFaV: Boosting Large Language Models for Zero-shot Fact Verification

TL;DR

ZeFaV is a zero-shot fact verification framework that enhances large language models' ability to verify claims by extracting relations, reorganizing evidence, and generating verdicts without task-specific training.

Contribution

Introduces ZeFaV, a novel zero-shot fact verification method leveraging in-context learning and relational evidence reorganization for improved accuracy.

Findings

Achieved results comparable to state-of-the-art methods on HoVer and FEVEROUS datasets.

Demonstrated the effectiveness of relation extraction and evidence reorganization in zero-shot verification.

Validated the approach's potential for multi-hop fact-checking tasks.

Abstract

In this paper, we propose ZeFaV - a zero-shot based fact-checking verification framework to enhance the performance on fact verification task of large language models by leveraging the in-context learning ability of large language models to extract the relations among the entities within a claim, re-organized the information from the evidence in a relationally logical form, and combine the above information with the original evidence to generate the context from which our fact-checking model provide verdicts for the input claims. We conducted empirical experiments to evaluate our approach on two multi-hop fact-checking datasets including HoVer and FEVEROUS, and achieved potential results results comparable to other state-of-the-art fact verification task methods.