+VeriRel: Verification Feedback to Enhance Document Retrieval for Scientific Fact Checking
This addresses the need for more effective evidence retrieval in scientific fact checking systems, though it is incremental as it builds on existing retrieval methods.
The paper tackles the problem of retrieving documents for scientific fact checking by proposing +VeriRel, which incorporates verification success into document ranking, resulting in consistently leading performance on three datasets (SciFact, SciFact-Open, and Check-Covid) and a positive impact on downstream verification.
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.