ECNU-SEA/SEA-A

Automated Peer Reviewing in Paper SEA: Standardization, Evaluation, and Analysis

Paper Link: https://arxiv.org/abs/2407.12857

Project Page: https://ecnu-sea.github.io/

🔥 News

• 🔥🔥🔥 SEA is accepted by EMNLP2024 !
• 🔥🔥🔥 We have made SEA series models (7B) public !

Model Description

⚠️ This is the SEA-A model for assessing the consistency between paper content and reviews.

The SEA-A model leverages the pre-trained sentence representation model SFR-Embedding-Mistral to encode the paper text and the corresponding review text into vector representations. Based on these representations, the query and key vectors are computed independently for the paper and the review. These vectors are then fed into the SEA-A model to produce a mismatch score, which quantifies the degree of inconsistency between the paper content and the review.

@inproceedings{yu2024automated,
  title={Automated Peer Reviewing in Paper SEA: Standardization, Evaluation, and Analysis},
  author={Yu, Jianxiang and Ding, Zichen and Tan, Jiaqi and Luo, Kangyang and Weng, Zhenmin and Gong, Chenghua and Zeng, Long and Cui, RenJing and Han, Chengcheng and Sun, Qiushi and others},
  booktitle={Findings of the Association for Computational Linguistics: EMNLP 2024},
  pages={10164--10184},
  year={2024}
}