Cover Image

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

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Corbeil, Jean-Philippe, Dada, Amin, Attendu, Jean-Michel, Abacha, Asma Ben, Sordoni, Alessandro, Caccia, Lucas, Beaulieu, François, Lin, Thomas, Kleesiek, Jens, Vozila, Paul
Format:	Preprint
Published:	2025
Subjects:	Computation and Language Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Less Finetuning, Better Retrieval: Rethinking LLM Adaptation for Biomedical Retrievers via Synthetic Data and Model Merging
by: Khattab, Sameh, et al.
Published: (2026)

MedRiskEval: Medical Risk Evaluation Benchmark of Language Models, On the Importance of User Perspectives in Healthcare Settings
by: Corbeil, Jean-Philippe, et al.
Published: (2025)

VERT: Reliable LLM Judges for Radiology Report Evaluation
by: Bologna, Federica, et al.
Published: (2026)

Overview of the MEDIQA-OE 2025 Shared Task on Medical Order Extraction from Doctor-Patient Consultations
by: Corbeil, Jean-Philippe, et al.
Published: (2025)

Overconfidence and Calibration in Medical VQA: Empirical Findings and Hallucination-Aware Mitigation
by: Byun, Ji Young, et al.
Published: (2026)

Towards Conditioning Clinical Text Generation for User Control
by: Koraş, Osman Alperen, et al.
Published: (2025)

Empowering Healthcare Practitioners with Language Models: Structuring Speech Transcripts in Two Real-World Clinical Applications
by: Corbeil, Jean-Philippe, et al.
Published: (2025)

IryoNLP at MEDIQA-CORR 2024: Tackling the Medical Error Detection & Correction Task On the Shoulders of Medical Agents
by: Corbeil, Jean-Philippe
Published: (2024)

Trade-offs in Ensembling, Merging and Routing Among Parameter-Efficient Experts
by: Lotfi, Sanae, et al.
Published: (2026)

MEDEC: A Benchmark for Medical Error Detection and Correction in Clinical Notes
by: Abacha, Asma Ben, et al.
Published: (2024)

Exploring Sparse Adapters for Scalable Merging of Parameter Efficient Experts
by: Arnob, Samin Yeasar, et al.
Published: (2025)

Training Plug-n-Play Knowledge Modules with Deep Context Distillation
by: Caccia, Lucas, et al.
Published: (2025)

Towards Modular LLMs by Building and Reusing a Library of LoRAs
by: Ostapenko, Oleksiy, et al.
Published: (2024)

Beyond Parameter Aggregation: Semantic Consensus for Federated Fine-Tuning of LLMs
by: Abourayya, Amr, et al.
Published: (2026)

Benchmarking LLMs and SLMs for patient reported outcomes
by: Marengo, Matteo, et al.
Published: (2024)

Disperse-Then-Merge: Pushing the Limits of Instruction Tuning via Alignment Tax Reduction
by: Fu, Tingchen, et al.
Published: (2024)

MeDiSumQA: Patient-Oriented Question-Answer Generation from Discharge Letters
by: Dada, Amin, et al.
Published: (2025)

MergeIT: From Selection to Merging for Efficient Instruction Tuning
by: Cai, Hongyi, et al.
Published: (2025)

BTReport: A Framework for Brain Tumor Radiology Report Generation with Clinically Relevant Features
by: Rivera, Juampablo E. Heras, et al.
Published: (2026)

Learning to Solve Complex Problems via Dataset Decomposition
by: Zhao, Wanru, et al.
Published: (2026)

El Instituto Nacional Indigenista en el municipio de Oxchuc, 1951-1971
by: Laurent Corbeil
Published: (2013)

Does Biomedical Training Lead to Better Medical Performance?
by: Dada, Amin, et al.
Published: (2024)

Guiding Language Model Reasoning with Planning Tokens
by: Wang, Xinyi, et al.
Published: (2023)

Does tenodesis of tensor fascia latae with hip abductors after proximal femoral resection and modular endoprosthetic reconstruction lead to functional improvements?
by: Ariane Lavoie‐Hudon, et al.
Published: (2025)

Fixed-Persona SLMs with Modular Memory: Scalable NPC Dialogue on Consumer Hardware
by: Braas, Martin, et al.
Published: (2025)

Automatic Fine-grained Segmentation-assisted Report Generation
by: Jonske, Frederic, et al.
Published: (2025)

Towards Synthetic Data Generation for Improved Pain Recognition in Videos under Patient Constraints
by: Nasimzada, Jonas, et al.
Published: (2024)

MAny: Merge Anything for Multimodal Continual Instruction Tuning
by: Gao, Zijian, et al.
Published: (2026)

Long-Document QA with Chain-of-Structured-Thought and Fine-Tuned SLMs
by: Liang, Zhuowen, et al.
Published: (2026)

Learning to Extract Context for Context-Aware LLM Inference
by: Kim, Minseon, et al.
Published: (2025)

Comprehensive Study on German Language Models for Clinical and Biomedical Text Understanding
by: Idrissi-Yaghir, Ahmad, et al.
Published: (2024)

Safeguard Fine-Tuned LLMs Through Pre- and Post-Tuning Model Merging
by: Farn, Hua, et al.
Published: (2024)

Centralisers of semi-simple elements are semidirect products
by: Digne, François, et al.
Published: (2025)

Decentralized Instruction Tuning: Conflict-Aware Splitting and Weight Merging
by: Choi, Minsik, et al.
Published: (2026)

Improved Multi-Task Brain Tumour Segmentation with Synthetic Data Augmentation
by: Ferreira, André, et al.
Published: (2024)

FineInstructions: Scaling Synthetic Instructions to Pre-Training Scale
by: Patel, Ajay, et al.
Published: (2026)

RISC-V Word-Size Modular Instructions for Residue Number Systems
by: Didier, Laurent-Stéphane, et al.
Published: (2024)

PivotMerge: Bridging Heterogeneous Multimodal Pre-training via Post-Alignment Model Merging
by: Shao, Zibo, et al.
Published: (2026)

Synthetic Data Aided Federated Learning Using Foundation Models
by: Abacha, Fatima, et al.
Published: (2024)

Attribute Structuring Improves LLM-Based Evaluation of Clinical Text Summaries
by: Gero, Zelalem, et al.
Published: (2024)