Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2604.10937 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913044743847936 |
|---|---|
| author | Jiang, Angqing Chen, Jianlyu Fang, Zhe Wang, Yongcan Li, Xinpeng Ding, Keyu Lian, Defu |
| author_facet | Jiang, Angqing Chen, Jianlyu Fang, Zhe Wang, Yongcan Li, Xinpeng Ding, Keyu Lian, Defu |
| contents | Effective medical text retrieval requires both high accuracy and low latency. While LLM-based embedding models possess powerful retrieval capabilities, their prohibitive latency and high computational cost limit their application in real-time scenarios. Furthermore, the lack of comprehensive and high-fidelity benchmarks hinders progress in Chinese medical text retrieval. In this work, we introduce the Chinese Medical Text Embedding Benchmark (CMedTEB), a benchmark spanning three kinds of practical embedding tasks: retrieval, reranking, and semantic textual similarity (STS). Distinct from purely automated datasets, CMedTEB is curated via a rigorous multi-LLM voting pipeline validated by clinical experts, ensuring gold-standard label quality while effectively mitigating annotation noise. On this foundation, we propose the Chinese Medical Asymmetric REtriever (CARE), an asymmetric architecture that pairs a lightweight BERT-style encoder for online query encoding with a powerful LLM-based encoder for offline document encoding. However, optimizing such an asymmetric retriever with two structurally different encoders presents distinctive challenges. To address this, we introduce a novel two-stage training strategy that progressively bridges the query and document representations. Extensive experiments demonstrate that CARE surpasses state-of-the-art symmetric models on CMedTEB, achieving superior retrieval performance without increasing inference latency. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_10937 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Benchmarking and Enabling Efficient Chinese Medical Retrieval via Asymmetric Encoders Jiang, Angqing Chen, Jianlyu Fang, Zhe Wang, Yongcan Li, Xinpeng Ding, Keyu Lian, Defu Information Retrieval Effective medical text retrieval requires both high accuracy and low latency. While LLM-based embedding models possess powerful retrieval capabilities, their prohibitive latency and high computational cost limit their application in real-time scenarios. Furthermore, the lack of comprehensive and high-fidelity benchmarks hinders progress in Chinese medical text retrieval. In this work, we introduce the Chinese Medical Text Embedding Benchmark (CMedTEB), a benchmark spanning three kinds of practical embedding tasks: retrieval, reranking, and semantic textual similarity (STS). Distinct from purely automated datasets, CMedTEB is curated via a rigorous multi-LLM voting pipeline validated by clinical experts, ensuring gold-standard label quality while effectively mitigating annotation noise. On this foundation, we propose the Chinese Medical Asymmetric REtriever (CARE), an asymmetric architecture that pairs a lightweight BERT-style encoder for online query encoding with a powerful LLM-based encoder for offline document encoding. However, optimizing such an asymmetric retriever with two structurally different encoders presents distinctive challenges. To address this, we introduce a novel two-stage training strategy that progressively bridges the query and document representations. Extensive experiments demonstrate that CARE surpasses state-of-the-art symmetric models on CMedTEB, achieving superior retrieval performance without increasing inference latency. |
| title | Benchmarking and Enabling Efficient Chinese Medical Retrieval via Asymmetric Encoders |
| topic | Information Retrieval |
| url | https://arxiv.org/abs/2604.10937 |