Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2605.13292 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866914563133276160 |
|---|---|
| author | Nigam, Shubham Kumar Sarkar, Suparnojit Patel, Piyush |
| author_facet | Nigam, Shubham Kumar Sarkar, Suparnojit Patel, Piyush |
| contents | Most existing medical dialogue systems operate in a single-turn question--answering paradigm or rely on template-based datasets, limiting conversational realism and multilingual applicability. We introduce IndicMedDialog, a parallel multi-turn medical dialogue dataset spanning English and nine Indic languages: Assamese, Bengali, Gujarati, Hindi, Marathi, Punjabi, Tamil, Telugu, and Urdu. The dataset extends MDDial with LLM-generated synthetic consultations, translated using TranslateGemma, verified by native speakers, and refined through a script-aware post-processing pipeline to correct phonetic, lexical, and character-spacing errors. Building on this dataset, we fine-tune IndicMedLM via parameter-efficient adaptation of a quantized small language model, incorporating optional patient pre-context to personalise multi-turn symptom elicitation. We evaluate against zero-shot multilingual baselines, conduct systematic error analysis across ten languages, and validate clinical plausibility through medical expert evaluation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_13292 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | IndicMedDialog: A Parallel Multi-Turn Medical Dialogue Dataset for Accessible Healthcare in Indic Languages Nigam, Shubham Kumar Sarkar, Suparnojit Patel, Piyush Computation and Language Artificial Intelligence Information Retrieval Machine Learning Most existing medical dialogue systems operate in a single-turn question--answering paradigm or rely on template-based datasets, limiting conversational realism and multilingual applicability. We introduce IndicMedDialog, a parallel multi-turn medical dialogue dataset spanning English and nine Indic languages: Assamese, Bengali, Gujarati, Hindi, Marathi, Punjabi, Tamil, Telugu, and Urdu. The dataset extends MDDial with LLM-generated synthetic consultations, translated using TranslateGemma, verified by native speakers, and refined through a script-aware post-processing pipeline to correct phonetic, lexical, and character-spacing errors. Building on this dataset, we fine-tune IndicMedLM via parameter-efficient adaptation of a quantized small language model, incorporating optional patient pre-context to personalise multi-turn symptom elicitation. We evaluate against zero-shot multilingual baselines, conduct systematic error analysis across ten languages, and validate clinical plausibility through medical expert evaluation. |
| title | IndicMedDialog: A Parallel Multi-Turn Medical Dialogue Dataset for Accessible Healthcare in Indic Languages |
| topic | Computation and Language Artificial Intelligence Information Retrieval Machine Learning |
| url | https://arxiv.org/abs/2605.13292 |