Accurate citation improves by reasoning about claim support not similarity
ReCite: Agentic Reasoning for Faithful Citation
Computation and Language
Summary
Finding the right sources to support academic claims is hard because many systems pick papers that sound related but don’t actually back up the point. To fix this, the authors developed ReCite, a method that thinks carefully about whether a paper really supports a claim rather than just matching similar words. Their approach checks and rechecks if the citation truly fits, making fewer mistakes than previous models. This helps make automated academic writing more trustworthy and accurate.
citation recommendationsemantic similarityreasoningretrieval-augmented modelsclaim-evidence consistencyself-correctionacademic writingliterature searchgenerative modelsquery planning
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.