English

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

Computation and Language 2024-11-19 v1 Artificial Intelligence

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.

Keywords

Cite

@article{arxiv.2411.11247,
  title  = {ZeFaV: Boosting Large Language Models for Zero-shot Fact Verification},
  author = {Son T. Luu and Hiep Nguyen and Trung Vo and Le-Minh Nguyen},
  journal= {arXiv preprint arXiv:2411.11247},
  year   = {2024}
}

Comments

This pre-print has been published in PRICAI 2024: Trends in Artificial Intelligence. The published version is available at https://doi.org/10.1007/978-981-96-0119-6_28

R2 v1 2026-06-28T20:03:02.284Z