LLM Manuscript Scoring System Validated Against Peer Review Outcomes

Researchers have developed a system called AIPR that uses large language models to score academic manuscripts for quality. This system was validated against peer-review outcomes for 300 submissions to the International Conference on Learning Representations (ICLR). AIPR's scores showed a significant ability to differentiate between rejected and accepted papers, and correlated with reviewer ratings, demonstrating its potential utility in assisting the peer-review process. AI

IMPACT Demonstrates LLMs can effectively score research papers, potentially streamlining academic peer review.

RANK_REASON The cluster describes a research paper detailing the validation of an LLM-based system for scoring academic manuscripts against peer-review outcomes. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.AI →

• arXiv
• International Conference on Learning Representations

• paper
• model release

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →