ReCite improves citation accuracy using reasoned claim verification
ReCite: Agentic Reasoning for Faithful Citation
Computation and Language
Summary
Academic writing relies on citing the right scientific papers to support statements. Existing automatic tools often pick papers that sound similar but don't really back up the point being made. The authors propose ReCite, a tool that reasons actively about claims, checks if citations logically support them, and fixes mistakes when needed. This method results in more accurate and trustworthy citations than previous systems that relied mainly on surface similarity.
What this means in practice
- •For academic writing tools developers: Enhance citation recommendation features by integrating claim-level reasoning to improve the logical accuracy of suggested references.
- •For legal document analysts: Support verification of citation claims in legal briefs by checking logical consistency between claims and referenced case law.
Authors
Yuyang Huang, Bobo Li, Jiajia Song, Yuzhe Ding, Chong Teng, Fei Li, Donghong Ji
Abstract
Accurate citations are the foundation of academic writing, tracing intellectual origins and substantiating core claims. However, manually navigating the growing volume of scientific literature is increasingly difficult, prompting reliance on automatic citation recommendation. While modern retrieval-augmented architectures have largely mitigated the fabrication of non-existent papers, current systems relying on semantic similarity struggle with misattribution, often citing authentic papers that fail to logically support the author's claim. To address this challenge, we argue that accurate citation requires a shift from similarity-based search to active, claim-level reasoning. We propose ReCite, a decoupled agentic framework that orchestrates location perception, intent-aware query planning, and reflective verification. Trained on synthesized reasoning trajectories, our agent verifies claim-evidence consistency and triggers self-correction loops when retrieved candidates lack logical support. Experiments demonstrate that our lightweight framework outperforms state-of-the-art massive generative models in strict citation accuracy. By grounding literature matching in verifiable logic rather than semantic overlap, ReCite establishes a reliable foundation for automated academic writing.