README.md

metadata

title: KaLM-Reranker-V1 Demo
colorFrom: indigo
colorTo: pink
sdk: gradio
sdk_version: 6.19.0
python_version: '3.13'
app_file: app.py
pinned: true
emoji: 🍒
short_description: A Gradio demo for KaLM-Reranker-V1 document reranking.

KaLM-Reranker-V1 Demo

This Space provides an online demo for KaLM-Reranker-V1, a fast but not late-interaction reranker for compressed document reranking.

Usage

1. Enter a query.
2. Enter candidate documents.
3. Separate candidate documents with one blank line.
4. Click Rerank.
5. The demo returns ranked documents with relevance scores.

Model

Default model:

KaLM-Embedding/KaLM-Reranker-V1-Nano

Citation

@misc{zhao2026kalmrerankerv1,
      title={KaLM-Reranker-V1: Fast but Not Late Interaction for Compressed Document Reranking}, 
      author={Xinping Zhao and Jiaxin Xu and Ziqi Dai and Xin Zhang and Shouzheng Huang and Danyu Tang and Xinshuo Hu and Meishan Zhang and Baotian Hu and Min Zhang},
      year={2026},
      eprint={2606.22807},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2606.22807}, 
} 

Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference