paper-with-me

홈 › Papers

Modular Expert Merging for Biomedical Retrieval

2026-02-04 · Sameh Khattab, Jean-Philippe Corbeil, Osman Alperen Koraş, Amin Dada, Julian Friedrich, François Beaulieu, Paul Vozila, Jens Kleesiek arxiv

Adapting general-purpose LLMs into domain-specialized dense retrievers typically requires large-scale training on mixed-domain data. We show that merging independently trained domain-specialized experts consistently exceeds this approach across four decoder-only LLM families (0.6B-7B), four merging methods, and twelve medical and general retrieval tasks from MTEB, suggesting that parameter-space composition captures complementary domain strengths that large-scale mixed-domain training averages out. To further maximize expert quality, we introduce Synthesize-Train-Merge (STM), a modular framework that synthesizes hard negatives with a top-tier LLM and fine-tunes domain-specialized experts via LoRA before merging them, without continual pre-training. Synthesized hard negatives yield the largest gains for smaller models, and STM achieves strong performance on biomedical retrieval tasks while maintaining competitive general-domain results across all four backbone families.

📄 PDF Abstract BibTeX arXiv:2602.04731

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

VerifAI: A Verifiable Open-Source Search Engine for Biomedical Question Answering

2026-01-16 · Miloš Košprdić, Adela Ljajić, Bojana Bašaragin, Darija Medvecki 외 arxiv

We introduce VerifAI, an open-source expert system for biomedical question answering that integrates retrieval-augmented generation (RAG) with a novel post-hoc claim verification mechanism. Unlike standard RAG systems, V…

Natural Language InferenceInformation RetrievalQuestion Answering

A Modular Approach for Clinical SLMs Driven by Synthetic Data with Pre-Instruction Tuning, Model Merging, and Clinical-Tasks Alignment

2025-05-15 · Jean-Philippe Corbeil, Amin Dada, Jean-Michel Attendu, Asma Ben Abacha 외

High computation costs and latency of large language models such as GPT-4 have limited their deployment in clinical settings. Small language models (SLMs) offer a cost-effective alternative, but their limited capacity re…

Domain Adaptation

Modular Retrieval for Generalization and Interpretation

2023-03-23 · Juhao Liang, Chen Zhang, Zhengyang Tang, Jie Fu 외

New retrieval tasks have always been emerging, thus urging the development of new retrieval models. However, instantiating a retrieval model for each new retrieval task is resource-intensive and time-consuming, especiall…

Language ModelingLanguage ModellingRetrieval

Exploring Sparse Adapters for Scalable Merging of Parameter Efficient Experts

2025-07-09 · Samin Yeasar Arnob, Zhan Su, Minseon Kim, Oleksiy Ostapenko 외

Merging parameter-efficient task experts has recently gained growing attention as a way to build modular architectures that can be rapidly adapted on the fly for specific downstream tasks, without requiring additional fi…

Fine-Grained Model Merging via Modular Expert Recombination

2026-02-06 · Haiyun Qiu, Xingyu Wu, Liang Feng, Kay Chen Tan arxiv

Model merging constructs versatile models by integrating task-specific models without requiring labeled data or expensive joint retraining. Although recent methods improve adaptability to heterogeneous tasks by generatin…