Papers
arxiv:2606.19037

Querit-Reranker: Training Compact Multilingual Rerankers via Efficient Label-Free Distribution Adaptation

Published on Jun 17
Authors:
,
,
,
,
,
,
,
,
,

Abstract

Querit-Reranker is a multilingual cross-encoder reranker family that achieves efficient adaptation through synthetic-query mining and checkpoint merging, delivering strong performance on multiple benchmark datasets.

Deployable multilingual rerankers must generalize across languages, domains, and target ranking tasks while remaining efficient enough for second-stage reranking. However, adapting them to new target distributions typically requires extensive task-specific relevance annotations, which are costly to obtain. We present Querit-Reranker, a family of multilingual cross-encoder rerankers trained with a data-centric pipeline for label-efficient adaptation. We instantiate it as Querit-Reranker-A0.4B, initialized from an in-house MoE backbone with 0.4B activated parameters, and Querit-Reranker-4B, initialized from Qwen3-Embedding-4B. Our pipeline first learns general relevance modeling from large-scale ranking-oriented data, then adapts to target distributions through synthetic-query mining with teacher scores as continuous soft labels. To consolidate complementary task-adapted strengths, we further merge checkpoints via spherical linear interpolation, obtaining a single deployable model without runtime ensembling overhead. Using Qwen3-Embedding-0.6B as the shared first-stage retriever, Querit-Reranker-A0.4B improves average nDCG@10 from 54.11 to 59.28 on BEIR and from 59.87 to 67.70 on MIRACL. On MTEB Multilingual v2 Reranking, it also substantially outperforms larger embedding-based baselines, while Querit-Reranker-4B further achieves state-of-the-art performance among publicly available models. We release both models on Hugging Face.

Community

Sign up or log in to comment

Models citing this paper 2

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2606.19037 in a dataset README.md to link it from this page.

Spaces citing this paper 9

Browse 9 spaces citing this paper

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.