---
license: apache-2.0
library_name: transformers
pipeline_tag: text-generation
---

# CoCoReviewBench Model

This repository contains a model checkpoint from the paper [CoCoReviewBench: A Completeness- and Correctness-Oriented Benchmark for AI Reviewers](https://huggingface.co/papers/2605.07905).

## Introduction
CoCoReviewBench is a benchmark designed for reliable and fine-grained evaluation of AI reviewers. It curates 3,900 papers from ICLR and NeurIPS, focusing on:
- **Completeness**: Evaluating by category to avoid penalizing models for issues missing in human references.
- **Correctness**: Filtering human reviews using reviewer-author-meta-reviewer discussions to ensure accuracy.

## Links
- **Paper**: [CoCoReviewBench: A Completeness- and Correctness-Oriented Benchmark for AI Reviewers](https://huggingface.co/papers/2605.07905)
- **Code**: [Official GitHub Repository](https://github.com/hexuandeng/CoCoReviewBench)

## Citation

```bibtex
@inproceedings{deng2026cocoreviewbench,
  title     = {{CoCoReviewBench}: A Completeness- and Correctness-Oriented Benchmark for {AI} Reviewers},
  author    = {Deng, Hexuan and Li, Yichen and Ke, Xiaopeng and Hu, Ruina and Wong, Derek F. and Wang, Yue and Liu, Xuebo and Huang, Dehao and Zhang, Min},
  booktitle = {Proceedings of the 43rd International Conference on Machine Learning},
  series    = {Proceedings of Machine Learning Research},
  publisher = {PMLR},
  year      = {2026},
  note      = {To appear},
  url       = {https://github.com/hexuandeng/CoCoReviewBench}
}
```