---
license: mit
library_name: transformers
pipeline_tag: text-ranking
---

# LimRank: Less is More for Reasoning-Intensive Information Reranking

This repository contains the `limrank-7b` model, based on `Qwen2.5-7B`, which was presented in the paper [LimRank: Less is More for Reasoning-Intensive Information Reranking](https://huggingface.co/papers/2510.23544).

LimRank demonstrates an efficient approach to adapt modern Large Language Models (LLMs) for reasoning-intensive information reranking tasks. This is achieved by leveraging `LIMRANK-SYNTHESIZER`, a reusable and open-source pipeline that generates minimal yet high-quality synthetic supervision data. Through this approach, LimRank achieves competitive performance on challenging benchmarks like BRIGHT and FollowIR, utilizing less than 5% of the data typically required by prior methods. The model also shows strong generalization capabilities across various downstream tasks, including scientific literature search and retrieval-augmented generation.

## Links
-   **Paper**: [LimRank: Less is More for Reasoning-Intensive Information Reranking](https://huggingface.co/papers/2510.23544)
-   **Code/GitHub Repository**: [https://github.com/SighingSnow/LimRank](https://github.com/SighingSnow/LimRank)
-   **Trained LimRank Model**: [songtingyu/limrank-7b](https://huggingface.co/songtingyu/limrank)
-   **Training Datasets**: [songtingyu/limrank-data](https://huggingface.co/datasets/songtingyu/limrank-data)
-   **Evaluation Results**: [sogntingyu/limrank-results](https://huggingface.co/datasets/songtingyu/limrank-results)
-   **Running Files for Reproduction**: [songtingyu/limrank-run-files](https://huggingface.co/datasets/songtingyu/limrank-run-files)

## Citation
If you find our paper useful, please cite our work:

```bibtex
@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}, 
}
```

## Acknowledgements
We would like to thank the authors of the following papers and repos for their open-source contributions. 
*   [rank1](https://github.com/orionw/rank1)
*   [ReasonIR](https://github.com/facebookresearch/ReasonIR) 
*   [MTEB](https://github.com/embeddings-benchmark/mteb)

## License
The model is released under the [MIT License](https://github.com/SighingSnow/LimRank/blob/main/LICENSE).