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

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

URL: http://arxiv.org/abs/2508.11122v1
Date: Thu, 14 Aug 2025 23:57:40 GMT
Title: +VeriRel: Verification Feedback to Enhance Document Retrieval for Scientific Fact Checking
Authors: Xingyu Deng, Xi Wang, Mark Stevenson,
Abstract summary: This paper proposes +VeriRel which includes verification success in the document ranking.<n> Experimental results on three scientific fact checking datasets demonstrate consistently leading performance by +VeriRel for document evidence retrieval.<n>It shows promising future work to evaluate fine-grained relevance when examining complex documents for advanced scientific fact checking.
Score: 11.88478056313921
License: http://creativecommons.org/licenses/by/4.0/
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.

Related papers

Comparing Knowledge Sources for Open-Domain Scientific Claim Verification [6.726255259929497]
We show that PubMed works better with specialized biomedical claims, while Wikipedia is more suited for everyday health concerns. We discuss the results, outline frequent retrieval patterns and challenges, and provide promising future directions.
arXiv Detail & Related papers (2024-02-05T09:57:15Z)
From Relevance to Utility: Evidence Retrieval with Feedback for Fact Verification [118.03466985807331]
We argue that, rather than relevance, for FV we need to focus on the utility that a claim verifier derives from the retrieved evidence.<n>We introduce the feedback-based evidence retriever(FER) that optimize the evidence retrieval process by incorporating feedback from the claim verifier.
arXiv Detail & Related papers (2023-10-18T02:59:38Z)
Give Me More Details: Improving Fact-Checking with Latent Retrieval [58.706972228039604]
Evidence plays a crucial role in automated fact-checking. Existing fact-checking systems either assume the evidence sentences are given or use the search snippets returned by the search engine. We propose to incorporate full text from source documents as evidence and introduce two enriched datasets.
arXiv Detail & Related papers (2023-05-25T15:01:19Z)
Complex Claim Verification with Evidence Retrieved in the Wild [73.19998942259073]
We present the first fully automated pipeline to check real-world claims by retrieving raw evidence from the web. Our pipeline includes five components: claim decomposition, raw document retrieval, fine-grained evidence retrieval, claim-focused summarization, and veracity judgment.
arXiv Detail & Related papers (2023-05-19T17:49:19Z)
Read it Twice: Towards Faithfully Interpretable Fact Verification by Revisiting Evidence [59.81749318292707]
We propose a fact verification model named ReRead to retrieve evidence and verify claim. The proposed system is able to achieve significant improvements upon best-reported models under different settings.
arXiv Detail & Related papers (2023-05-02T03:23:14Z)
SciFact-Open: Towards open-domain scientific claim verification [61.288725621156864]
We present SciFact-Open, a new test collection designed to evaluate the performance of scientific claim verification systems. We collect evidence for scientific claims by pooling and annotating the top predictions of four state-of-the-art scientific claim verification models. We find that systems developed on smaller corpora struggle to generalize to SciFact-Open, exhibiting performance drops of at least 15 F1.
arXiv Detail & Related papers (2022-10-25T05:45:00Z)
Generating Scientific Claims for Zero-Shot Scientific Fact Checking [54.62086027306609]
Automated scientific fact checking is difficult due to the complexity of scientific language and a lack of significant amounts of training data. We propose scientific claim generation, the task of generating one or more atomic and verifiable claims from scientific sentences. We also demonstrate its usefulness in zero-shot fact checking for biomedical claims.
arXiv Detail & Related papers (2022-03-24T11:29:20Z)
Assisting the Human Fact-Checkers: Detecting All Previously Fact-Checked Claims in a Document [27.076320857009655]
Given an input document, it aims to detect all sentences that contain a claim that can be verified by some previously fact-checked claims. The output is a re-ranked list of the document sentences, so that those that can be verified are ranked as high as possible. Our analysis demonstrates the importance of modeling text similarity and stance, while also taking into account the veracity of the retrieved previously fact-checked claims.
arXiv Detail & Related papers (2021-09-14T13:46:52Z)
AmbiFC: Fact-Checking Ambiguous Claims with Evidence [57.7091560922174]
We present AmbiFC, a fact-checking dataset with 10k claims derived from real-world information needs. We analyze disagreements arising from ambiguity when comparing claims against evidence in AmbiFC. We develop models for predicting veracity handling this ambiguity via soft labels.
arXiv Detail & Related papers (2021-04-01T17:40:08Z)

This list is automatically generated from the titles and abstracts of the papers in this site.