AI RESEARCH
Scoring, Reasoning, and Selecting the Best! Ensembling Large Language Models via a Peer-Review Process
arXiv CS.AI
•
ArXi:2512.23213v3 Announce Type: replace-cross We propose LLM-PeerReview, an unsupervised LLM Ensemble method that selects the most ideal response from multiple LLM-generated candidates for each query, harnessing the collective wisdom of multiple models with diverse strengths. LLM-PeerReview is built on a novel, peer-review-inspired framework that offers a transparent and interpretable mechanism, while remaining fully unsupervised for flexible adaptability and generalization.