Understanding before verifying: Claim normalization for automated citation verification
2026-08-31 • Information Retrieval
Information Retrieval
AI summaryⓘ
The authors study how verifying citations in research can be improved. They find that existing two-step methods struggle because they don't simplify complicated citing statements first. To fix this, they introduce a new three-step method called Claim-Normalized Citation Verification (CNCV), which first rewrites the citing claim to make it clearer, then finds supporting evidence, and finally checks the citation’s accuracy. Their approach significantly improves verification accuracy, making automatically retrieved evidence as good as manually gathered evidence for checking citations.
citation verificationclaim normalizationevidence retrievalfact-checkingencoding modelsgenerative large language modelsmacro F1 scoreclassificationproposition entanglementperspective mismatch
Authors
Yifan He, Mengjia Wu, Siming Deng, Yi Zhang
Abstract
Citation accuracy has been studied for decades because of its importance to research reliability. Content-level citation verification assesses the reliability of scholarly claims. Recent work adopts a two-stage retrieval-classification framework inherited from fact-checking. However, this design overlooks the complexity of the raw citing claim and introduces three issues into the verification system, namely scope mismatch, perspective mismatch, and proposition entanglement. These issues increase the difficulty of retrieval and classification, thereby limiting model performance. Motivated by this gap, we propose claim normalization, which applies three rewriting strategies to the raw citing claim before retrieval and classification, allowing each downstream model to perform a single, well-defined task. Building on this method, we develop Claim-Normalized Citation Verification (CNCV), a new three-stage framework consisting of claim normalization, evidence retrieval with grounding, and citation classification. We evaluate CNCV across 18 classifiers using a factorial experiment on human-annotated citation instances. Compared with the prior two-stage framework, CNCV improves macro F1 by an average of 12% for encoders and 10% for generative LLMs, driven by improved evidence quality, the dominant factor identified in our experiments. Evidence retrieved from automatically normalized claims yields downstream classification performance statistically equivalent to that obtained with manually annotated evidence.