KaLM Reranker — Compressed Document Reranking

Rerank documents efficiently with KaLM-Embedding/KaLM-Reranker-V1-Small.

1 10
Compression factor (encoder chunk pooling)
1× = no sequence-length reduction; 32× = strongest pooling.

Reranked results

Try an example

About KaLM-Reranker-V1 — A fast but not late-interaction reranker that pre-encodes passages and uses cross-attention to model fine-grained query-document relevance. Model card · Homepage

@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}, 
}