New multilingual reranker models trained efficiently for diverse tasks

Researchers have developed Querit-Reranker, a new family of multilingual cross-encoder rerankers designed for efficient adaptation to various ranking tasks without requiring extensive labeled data. The models are trained using a pipeline that leverages synthetic query mining and teacher scores as soft labels, and checkpoints can be merged to create a single deployable model. Querit-Reranker-A0.4B demonstrated significant improvements on benchmarks like BEIR and MIRACL, while Querit-Reranker-4B achieved state-of-the-art performance among publicly available models. Both models are available on Hugging Face. AI

IMPACT Introduces a more efficient method for adapting multilingual rerankers, potentially lowering the barrier for deploying advanced search and retrieval systems.

RANK_REASON Academic paper detailing a new model architecture and training methodology. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.IR (Information Retrieval) →

• BEIR
• Hugging Face
• MTEB Multilingual v2 Reranking
• Querit-Reranker
• Querit-Reranker-4B
• Querit-Reranker-A0.4B
• Qwen3-Embedding-0.6B
• Qwen3-Embedding-4B

• paper
• model release

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →