Computer Science > Computation and Language

arXiv:2607.26066 (cs) | Submitted on 21 Jun 2026

Do Methods Support the Claims? Intra-Paper Verification for Peer Review

Authors: Ranjitha Shivaprasad Ballakuraya, Arash Mahyari, Ashok Srinivasan

Abstract

The growing volume of scientific submissions has intensified interest in leveraging large language models (LLMs) to assist peer review, particularly in 2026 as AI-assisted reviewing becomes more common. Existing automated novelty assessment methods typically compare a paper’s claimed contributions against prior literature, implicitly assuming that these contributions are faithfully realized in the work itself. However, human reviewers often challenge novelty claims not because similar ideas already exist, but because the methodological evidence presented within the paper does not adequately support them. This internal misalignment between claimed contributions and methodological realization is rarely examined by current LLM-based review systems.

To address this gap, we introduce intra-paper claim verification, a framework that evaluates whether novelty claims articulated in a paper are substantiated by the methods used to implement them. The framework uses an LLM to extract novelty claims from the introduction, retrieve claim-relevant methodological evidence, and assess whether the methods support the stated contributions. Assessment is guided by reviewer-inspired evaluation criteria inductively derived from human peer reviews collected from 182 ICLR 2025 papers. These criteria capture recurring reviewer concerns related to novelty, methodology, clarity, and other issues, and are used to generate structured, reviewer-style assessments of claim substantiation.

We evaluate the framework by comparing LLM-generated review comments against human reviewer concerns on a balanced subset of accepted and rejected papers. Human evaluation demonstrates significant alignment between framework-generated assessments and human reviewer concerns, particularly for novelty-related issues. BERTScore further distinguishes corresponding human-LLM review pairs from mismatched controls, indicating that the framework captures concerns consistent with human reviewer observations.

Additional Information

Comments: 9 pages, 8 figures. Source code, prompts, evaluation materials, and supporting data available at: https://github.com/Ranjitha2493/intra-paper-claim-method-verification

Subjects: Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Digital Libraries (cs.DL)

Cite as: arXiv:2607.26066 [cs.CL] (or arXiv:2607.26066v1 [cs.CL] for this version)

via ArXiv CL