What Makes Medical Claims (Un)Verifiable? Analyzing Entity and Relation Properties for Fact Verification

TL;DR

This work tackles the verifiability of biomedical claims by decomposing claims into entities and relations and building BEAR-Fact, a Twitter-based corpus annotated with entity/relation structures, evidence, and veracity verdicts. It shows that positive entity–relation patterns (e.g., causation) are more readily verifiable than negated forms, and that annotators primarily reformulate queries to canonical entity names during evidence retrieval. The study compares in-house annotations with crowdsourcing, finding domain expertise has limited impact on reliability, and demonstrates that a fine-tuned RoBERTa model can distinguish verifiable claims with $F_1 = 0.82$ for verifiable cases and $F_1 = 0.27$ for unverifiable cases. The dataset and findings offer a foundation to improve automatic biomedical fact verification and evidence retrieval in user-generated content.

Abstract

Biomedical claim verification fails if no evidence can be discovered. In these cases, the fact-checking verdict remains unknown and the claim is unverifiable. To improve upon this, we have to understand if there are any claim properties that impact its verifiability. In this work we assume that entities and relations define the core variables in a biomedical claim's anatomy and analyze if their properties help us to differentiate verifiable from unverifiable claims. In a study with trained annotation experts we prompt them to find evidence for biomedical claims, and observe how they refine search queries for their evidence search. This leads to the first corpus for scientific fact verification annotated with subject-relation-object triplets, evidence documents, and fact-checking verdicts (the BEAR-Fact corpus). We find (1) that discovering evidence for negated claims (e.g., X-does-not-cause-Y) is particularly challenging. Further, we see that annotators process queries mostly by adding constraints to the search and by normalizing entities to canonical names. (2) We compare our in-house annotations with a small crowdsourcing setting where we employ medical experts and laypeople. We find that domain expertise does not have a substantial effect on the reliability of annotations. Finally, (3), we demonstrate that it is possible to reliably estimate the success of evidence retrieval purely from the claim text~(.82\F), whereas identifying unverifiable claims proves more challenging (.27\F). The dataset is available at http://www.ims.uni-stuttgart.de/data/bioclaim.