IndicMedDialog: A Parallel Multi-Turn Medical Dialogue Dataset for Accessible Healthcare in Indic Languages

Accepted in BioNLP @ ACL 2026 Conference.

Conversational artificial intelligence has the potential to assist users in preliminary medical consultations, particularly in settings where access to healthcare professionals is limited. However, many existing medical dialogue systems operate in a single-turn question--answering paradigm or rely on template-based datasets, limiting conversational realism and multilingual applicability. In this work, we introduce IndicMedDialog, a multilingual multi-turn medical dialogue dataset designed to simulate realistic physician--patient consultations. The dataset extends the MDDial corpus by generating synthetic consultations using large language models and further expands them into a parallel multi-turn medical dialogue dataset spanning English and nine Indic languages:Assamese, Bengali, Gujarati, Hindi, Marathi, Punjabi, Tamil, Telugu and Urdu.

Building on this dataset, we develop IndicMedDialog, a conversational medical model trained using parameter-efficient fine-tuning on quantized small language models, enabling deployment without high-end computational infrastructure. Our framework additionally incorporates optional patient pre-context information (age, gender, allergies, weight, allergies) to personalize the consultation process. Experimental results demonstrate that the proposed system can effectively perform symptom elicitation through multi-turn dialogue and generate diagnostic recommendations.