TurkishMedLLM: A Source-Grounded and Safety-Aware Turkish Medical LLM for Clinical Decision Support and Digital Health Applications
Abstract
Large language models are increasingly being explored for clinical decision support and digital health applications. However, most high-performing medical LLMs, datasets, benchmarks, and evaluation pipelines have been developed primarily for English, while their reliable use in low-resource medical languages such as Turkish remains limited. Turkish medical communication requires locally adapted, source-grounded, and safety-aware language model infrastructure because direct use of general-purpose or English-centric LLMs may produce non-localized, unsupported, mistranslated, or clinically unsafe responses. Existing medical LLM approaches commonly use supervised fine-tuning or retrieval-augmented generation to improve domain adaptation and factual grounding. However, many existing solutions still provide limited transparency in corpus construction, weak source traceability, insufficient clinical safety control, and incomplete evaluation of retrieval quality, response faithfulness, and medical caution. To address these limitations, this study presents TurkishMedLLM, a source-grounded and safety-aware Turkish medical large language model for clinical decision support and digital health applications. The proposed framework integrates multi-source Turkish medical data ingestion, flexible schema detection, duplicate removal, quality filtering, supervised fine-tuning preparation, recursive article chunking, local BGE-M3 embedding generation, ChromaDB-based vector indexing,…
Read the paper
Related studies
- Knowledge Management Perspective of Generative Artificial Intelligence
- Navigating Generative Artificial Intelligence Promises and Perils for Knowledge and Creative Work
- Characterizing the evolving research on enterprise content management
- Large language models and multimodal foundation models for precision oncology
- From Generative AI to Extended Reality: Multidisciplinary Perspectives on the Challenges, Opportunities, and Future of Educational Computing
- Generative Artificial Intelligence: A New Engine for Advancing Environmental Science and Engineering
Go deeper in Evidence Hub
Evidence Hub adds a study data sheet (design, sample size, evidence level, key numbers), an AI summary and a chat grounded in the paper's text.