+VeriRel: Verification Feedback to Enhance Document Retrieval for Scientific Fact Checking

TL;DR

+VeriRel enhances scientific fact checking by integrating verification success into document retrieval, leading to improved evidence identification and verification accuracy across multiple datasets.

Contribution

The paper introduces +VeriRel, a novel approach that incorporates verification feedback into document ranking for scientific fact checking.

Findings

+VeriRel outperforms existing retrieval methods on three datasets.

Verification feedback improves downstream fact verification accuracy.

The approach demonstrates consistent performance gains across datasets.

Abstract

Identification of appropriate supporting evidence is critical to the success of scientific fact checking. However, existing approaches rely on off-the-shelf Information Retrieval algorithms that rank documents based on relevance rather than the evidence they provide to support or refute the claim being checked. This paper proposes +VeriRel which includes verification success in the document ranking. Experimental results on three scientific fact checking datasets (SciFact, SciFact-Open and Check-Covid) demonstrate consistently leading performance by +VeriRel for document evidence retrieval and a positive impact on downstream verification. This study highlights the potential of integrating verification feedback to document relevance assessment for effective scientific fact checking systems. It shows promising future work to evaluate fine-grained relevance when examining complex documents for advanced scientific fact checking.