OpenReviewer: Open-source 8B LLM fine-tuned on 79K expert reviews generates critical peer reviews for AI papers
alejandroll10 · x · 2026-08-09
OpenReviewer is an open-source system for generating high-quality peer reviews of machine learning and AI conference papers. At its core is Llama-OpenReviewer-8B, an 8B parameter language model fine-tuned on 79,000 expert reviews from top conferences like ICLR and NeurIPS.
Key features include:
- Specialized model fine-tuned on 79K expert reviews
- Generates realistic, critical reviews matching human standards
- Structured output following conference-specific templates
- PDF processing extracting full text including equations and tables
- Open source for research and development
Evaluation on 400 test papers shows significant improvement over baselines.
More from Research
- Retriever: A Framework for Asynchronous, Closed-Loop Robot Agents — ZeYanjie · 2026-08-24
- Converting GMMs ↔ PEFs for fast KLD approximation — FrnkNlsn · 2026-08-24
- Netflix details its production LLM judge: hundreds of thousands of recommendations scored weekly — omarsar0 · 2026-08-24
- Nature Comment: Provenance, not interpretability, grounds trust in autonomous science — gabepgomes · 2026-08-24
- New Architecture RHEA: Train 1B Model on 8GB VRAM — zemondza · 2026-08-24
- Trained two 16M-param models to do generative CAD with real physics — debreuil · 2026-08-24