SOURCE-LINKED INTELLIGENCE

More Criticism Does Not Make a Better Review: EquiReview-R

arXiv · AI, language, vision and robotics · article · Sep 3, 2026 · UTC

AI reviewers can now produce many specific criticisms, but more criticism is not necessarily a better review. A review may miss a consequential weakness or retain an allegation that available evidence does not support. These failures require opposite corrections, yet generation-oriented systems and aggregate measures obscure the distinction. We therefore recast AI-assisted review as evidence-guided refinement of a structured concern set, with omission and overcritique treated as separate risks. Building on this formulation, we introduce EquiReview-R, which resolves existing concerns against lo

Read original source ↗ Open in workspace

recordType

paper

region

Global