Official repository for paper LimRank: Less is More for Reasoning-Intensive Information Reranking.
| Resource | Description |
|---|---|
| songtingyu/limrank-7b | The trained LimRank model based on Qwen2.5-7B |
| songtingyu/limrank-data | The training datasets for limrank-7b |
| sogntingyu/limrank-results | The evaluation results of limrank-7b |
| songtingyu/limrank-run-files | The running files to reproduce the results. |
To reproduce the experiments, you can use the following code with uv for fast, reliable dependency management:
conda activate limrank_env
pip install -r requirements.txtPlease refer to the Rerank Experiments for more details.
Please refer to the LimRank-GPQA for more details.
If you think our paper is useful, you can cite:
@misc{song2025limrankreasoningintensiveinformationreranking,
title={LimRank: Less is More for Reasoning-Intensive Information Reranking},
author={Tingyu Song and Yilun Zhao and Siyue Zhang and Chen Zhao and Arman Cohan},
year={2025},
eprint={2510.23544},
archivePrefix={arXiv},
primaryClass={cs.CL},
url={https://arxiv.org/abs/2510.23544},
}We would like to thank the authors of the following papers and repos for their open-source contributions.