Evidence-Based Temporal Fact Verification

TL;DR

This paper introduces an end-to-end approach for temporal fact verification that leverages temporal information extraction, event modeling, and large language models to improve accuracy in verifying time-sensitive claims.

Contribution

It presents a novel dataset and a comprehensive method combining temporal reasoning and large language models for more accurate temporal fact verification.

Findings

Significant improvement over previous methods in temporal claim verification accuracy.

Effective modeling of event relationships and chronological proximity enhances evidence retrieval.

Demonstrated state-of-the-art performance on curated temporal fact datasets.

Abstract

Automated fact verification plays an essential role in fostering trust in the digital space. Despite the growing interest, the verification of temporal facts has not received much attention in the community. Temporal fact verification brings new challenges where cues of the temporal information need to be extracted and temporal reasoning involving various temporal aspects of the text must be applied. In this work, we propose an end-to-end solution for temporal fact verification that considers the temporal information in claims to obtain relevant evidence sentences and harness the power of large language model for temporal reasoning. Recognizing that temporal facts often involve events, we model these events in the claim and evidence sentences. We curate two temporal fact datasets to learn time-sensitive representations that encapsulate not only the semantic relationships among the events, but also their chronological proximity. This allows us to retrieve the top-k relevant evidence sentences and provide the context for a large language model to perform temporal reasoning and outputs whether a claim is supported or refuted by the retrieved evidence sentences. Experiment results demonstrate that the proposed approach significantly enhances the accuracy of temporal claim verification, thereby advancing current state-of-the-art in automated fact verification.