Beyond "Not Novel Enough": Enriching Scholarly Critique with LLM-Assisted Feedback
This addresses the strain on reviewer capacity in high-volume fields like NLP by supporting more rigorous and transparent peer review without replacing human expertise.
The paper tackles the problem of automated novelty assessment in peer review by developing a structured LLM-assisted method that models expert reviewer behavior, achieving 86.5% alignment with human reasoning and 75.3% agreement on novelty conclusions on ICLR 2025 submissions.
Novelty assessment is a central yet understudied aspect of peer review, particularly in high volume fields like NLP where reviewer capacity is increasingly strained. We present a structured approach for automated novelty evaluation that models expert reviewer behavior through three stages: content extraction from submissions, retrieval and synthesis of related work, and structured comparison for evidence based assessment. Our method is informed by a large scale analysis of human written novelty reviews and captures key patterns such as independent claim verification and contextual reasoning. Evaluated on 182 ICLR 2025 submissions with human annotated reviewer novelty assessments, the approach achieves 86.5% alignment with human reasoning and 75.3% agreement on novelty conclusions - substantially outperforming existing LLM based baselines. The method produces detailed, literature aware analyses and improves consistency over ad hoc reviewer judgments. These results highlight the potential for structured LLM assisted approaches to support more rigorous and transparent peer review without displacing human expertise. Data and code are made available.