ReCite: Agentic Reasoning for Faithful Citation
ReCite is an agentic citation framework using claim-level reasoning and verification, outperforming large generative models in strict citation accuracy.
ReCite is a decoupled agentic framework that orchestrates location perception, intent-aware query planning, and reflective verification for citation recommendation. Trained on synthesized reasoning trajectories, the agent verifies claim-evidence consistency and triggers self-correction loops when retrieved candidates lack logical support. Experiments show the lightweight framework outperforms state-of-the-art massive generative models in strict citation accuracy, addressing misattribution where cited papers are real but logically unsupportive.
- Moves citation from similarity-based retrieval to active claim-level reasoning with verification.
- Self-correction loops trigger when retrieved candidates lack logical support for the claim.
- Lightweight framework beats state-of-the-art massive generative models on strict citation accuracy.
From the original article
1 min read at arxiv.orgAccurate 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.
By Yuyang Huang · arxiv.org
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.