SOURCE-LINKED INTELLIGENCE

AtomCite: Verification and Correction of Supplied Page-Level Citations in Multi-Page Documents

arXiv · AI, language, vision and robotics · article · Sep 5, 2026 · UTC

Large language models answering questions over multi-page documents are expected to cite the supporting pages, yet supplied citations are sometimes inaccurate, and current evaluations score citations at generation time or against text passages: no existing benchmark evaluates whether a system can verify and correct a page-level citation already attached to an answer. We propose AtomCite, an agentic framework that parses an answer into claims, checks each claim against the image of its cited page, and applies a deterministic repair policy. To evaluate it, we introduce DocCite, to our knowledge

Read original source ↗ Open in workspace

recordType

paper

region

Global