ffjasonyu commited on
Commit
8d17d5f
·
verified ·
1 Parent(s): 9c23960

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +11 -11
README.md CHANGED
@@ -9,8 +9,7 @@ datasets:
9
 
10
  ## Automated Peer Reviewing in Paper SEA: Standardization, Evaluation, and Analysis
11
 
12
- Paper Link: ...
13
- <!-- https://arxiv.org/abs/2311.09278 -->
14
 
15
  Project Page: https://ecnu-sea.github.io/
16
 
@@ -22,13 +21,14 @@ Project Page: https://ecnu-sea.github.io/
22
  ## Model Description
23
  The SEA-S model aims to integrate all reviews for each paper into one to eliminate redundancy and errors, focusing on the major advantages and disadvantages of the paper. Specifically, we first utilize GPT-4 to integrate multiple reviews of a paper into one (From [ECNU-SEA/SEA_data](https://huggingface.co/datasets/ECNU-SEA/SEA_data)) that is in a unified format and criterion with constructive contents, and form an instruction dataset for SFT. After that, we fine-tune [Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) to distill the knowledge of GPT-4. Therefore, SEA-S provides a novel paradigm for integrating peer review data in an unified format across various conferences.
24
 
25
- <!-- ```bibtex
26
- @misc{yu2024sea,
27
- title={Automated Peer Reviewing in Paper SEA: Standardization, Evaluation, and Analysis},
28
- author={Jianxiang Yu and Zichen Ding and Jiaqi Tan and Kangyang Luo and Zhenmin Weng and Chegnhua Gong and Long Zeng and Renjing Cui and Chengcheng Han and Qiushi Sun and Zhiyong Wu and Yunshi Lan and Xiang Li},
29
- year={2024},
30
- eprint={2406.26456},
31
- archivePrefix={arXiv},
32
- primaryClass={cs.AI}
 
33
  }
34
- ``` -->
 
9
 
10
  ## Automated Peer Reviewing in Paper SEA: Standardization, Evaluation, and Analysis
11
 
12
+ Paper Link: https://arxiv.org/abs/2407.12857
 
13
 
14
  Project Page: https://ecnu-sea.github.io/
15
 
 
21
  ## Model Description
22
  The SEA-S model aims to integrate all reviews for each paper into one to eliminate redundancy and errors, focusing on the major advantages and disadvantages of the paper. Specifically, we first utilize GPT-4 to integrate multiple reviews of a paper into one (From [ECNU-SEA/SEA_data](https://huggingface.co/datasets/ECNU-SEA/SEA_data)) that is in a unified format and criterion with constructive contents, and form an instruction dataset for SFT. After that, we fine-tune [Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) to distill the knowledge of GPT-4. Therefore, SEA-S provides a novel paradigm for integrating peer review data in an unified format across various conferences.
23
 
24
+ ```bibtex
25
+ @misc{yu2024automatedpeerreviewingpaper,
26
+ title={Automated Peer Reviewing in Paper SEA: Standardization, Evaluation, and Analysis},
27
+ author={Jianxiang Yu and Zichen Ding and Jiaqi Tan and Kangyang Luo and Zhenmin Weng and Chenghua Gong and Long Zeng and Renjing Cui and Chengcheng Han and Qiushi Sun and Zhiyong Wu and Yunshi Lan and Xiang Li},
28
+ year={2024},
29
+ eprint={2407.12857},
30
+ archivePrefix={arXiv},
31
+ primaryClass={cs.CL},
32
+ url={https://arxiv.org/abs/2407.12857},
33
  }
34
+ ```