Get Started
Home
Topics
Search
Library
Research questionHow can dense retrievers specialize for biomedical search without sacrificing general-domain retrieval?Training retrievers across biomedical and general domains can be costly, and mixed-domain training may blur capabilities that are useful in specialized settings. The central difficulty is improving biomedical retrieval while preserving broad-domain performance.
AI
Evaluation & Benchmarks
Health
Information Retrieval
LLM Pretraining & Post-training
Machine Learning
Natural Language Processing
Latest papersRecent research connected to this question, newest first.Modular Expert Merging for Biomedical RetrievalThe evidence concerns four decoder-only LLM families ranging from 0.6B to 7B parameters, evaluated with four parameter-merging methods on twelve medical and general MTEB retrieval tasks. It also examines LoRA-based domain experts trained with synthesized hard negatives, without continual pre-training.research paper · Sep 2, 2026
Related questions
How should math-focused retrievers be evaluated when generic benchmarks miss fine-grained relevance?How can private outsourced vector retrieval scale to millions of documents without unacceptable latency or search-quality loss?How can compact text embedding models improve retrieval and generalization through better training and data quality?How can video-based sign dictionary retrieval generalize across signers and unseen languages?