KaLM-Reranker-V1:快速但非延迟交互的压缩文档重排序器
阅读原文· arxiv.orgKaLM-Reranker-V1 是一种快速但非延迟交互(FBNL)重排序器,采用编码器-解码器架构。编码器使用 Matryoshka 嵌入池化预编码段落,解码器建模系统指令、用户指令和查询意图,再通过交叉注意力捕获查询与段落间的相关性,实现解耦计算并保持高效。模型提供 Nano(0.27B)、Small(1B)和 Large(4B)三种激活参数尺寸。在 BEIR 上达到 SOTA,与 Qwen3-Reranker 系列持平;在 MIRACL 上未经大量多语言训练仍表现优异;在 LMEB 上,0.27B Nano 模型可与 7-12B 嵌入模型竞争。
As retrieval systems scale, high-quality reranking becomes increasingly important. However, most existing rerankers, whether encoder-based or decoder-based, jointly encode the query and passage, tightly coupling their computation and limiting deployment efficiency as well as flexibility. We present KaLM-Reranker-V1, a fast but not late-interaction (FBNL) reranker that decouples query and passage computation while retaining expressive relevance modeling. Built on an encoder-decoder architecture, KaLM-Reranker-V1 uses the encoder to pre-encode passages with Matryoshka embedding pooling, while the decoder models the system instruction, user instruction, and query intent; cross-attention then captures relevance between the query context and passage representations. This design makes KaLM-Reranker-V1 efficient through decoupled passage encoding, yet not late interaction, by preserving rich relevance modeling through cross-attention. We instantiate KaLM-Reranker-V1 in three sizes, Nano, Small, and Large, with 0.27B, 1B, and 4B activated parameters, respectively. Extensive experiments on BEIR, MIRACL, and LMEB demonstrate that KaLM-Reranker-V1 achieves strong reranking performance with superior efficiency. On BEIR, KaLM-Reranker-V1 achieves state-of-the-art performance, on par with strong industrial models such as the Qwen3-Reranker series; on MIRACL, despite not being extensively trained on multilingual data, KaLM-Reranker-V1 still shows excellent reranking performance. Moreover, on LMEB, reranking models demonstrate a clear advantage, with even the 0.27B Nano model remaining competitive with 7-12B embedding models.