@inproceedings{nigam-etal-2026-indicmeddialog,
title = "{I}ndic{M}ed{D}ialog: A Parallel Multi-Turn Medical Dialogue Dataset for Accessible Healthcare in {I}ndic Languages",
author = "Nigam, Shubham and
Sarkar, Suparnojit and
Patel, Piyush",
editor = "Demner-Fushman, Dina and
Ananiadou, Sophia and
Roberts, Kirk and
Tsujii, Junichi",
booktitle = "{B}io{NLP} 2026",
month = jul,
year = "2026",
address = "San Diego, California",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.bionlp-1.84/",
pages = "1041--1055",
ISBN = "979-8-89176-434-7",
abstract = "We present 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 the MDDial corpus 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 introduced during automatic translation. Building on this dataset, we fine-tune IndicMedLM via parameter-efficient adaptation (LoRA) of a quantized small language model, incorporating an optional patient pre-context to personalise multi-turn symptom elicitation. We evaluate IndicMedLM against zero-shot multilingual baselines across ten languages and conduct systematic error analysis, identifying five failure modes: Instruction Drift, Label Collapse, Cross-Domain Confusion, Tokenization Failure, and Paraphrase-over-Label Generation. Results show strong post-processed diagnostic accuracy in Hindi, Marathi, and Bengali, while Assamese, Tamil, and Telugu remain in an extreme failure tier attributable to base-model tokenizer gaps, a finding with direct patient safety implications. Medical expert evaluation confirms the clinical plausibility and safety of the generated consultations."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nigam-etal-2026-indicmeddialog">
<titleInfo>
<title>IndicMedDialog: A Parallel Multi-Turn Medical Dialogue Dataset for Accessible Healthcare in Indic Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shubham</namePart>
<namePart type="family">Nigam</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Suparnojit</namePart>
<namePart type="family">Sarkar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Piyush</namePart>
<namePart type="family">Patel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>BioNLP 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dina</namePart>
<namePart type="family">Demner-Fushman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sophia</namePart>
<namePart type="family">Ananiadou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kirk</namePart>
<namePart type="family">Roberts</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Junichi</namePart>
<namePart type="family">Tsujii</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, California</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-434-7</identifier>
</relatedItem>
<abstract>We present 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 the MDDial corpus 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 introduced during automatic translation. Building on this dataset, we fine-tune IndicMedLM via parameter-efficient adaptation (LoRA) of a quantized small language model, incorporating an optional patient pre-context to personalise multi-turn symptom elicitation. We evaluate IndicMedLM against zero-shot multilingual baselines across ten languages and conduct systematic error analysis, identifying five failure modes: Instruction Drift, Label Collapse, Cross-Domain Confusion, Tokenization Failure, and Paraphrase-over-Label Generation. Results show strong post-processed diagnostic accuracy in Hindi, Marathi, and Bengali, while Assamese, Tamil, and Telugu remain in an extreme failure tier attributable to base-model tokenizer gaps, a finding with direct patient safety implications. Medical expert evaluation confirms the clinical plausibility and safety of the generated consultations.</abstract>
<identifier type="citekey">nigam-etal-2026-indicmeddialog</identifier>
<location>
<url>https://aclanthology.org/2026.bionlp-1.84/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>1041</start>
<end>1055</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T IndicMedDialog: A Parallel Multi-Turn Medical Dialogue Dataset for Accessible Healthcare in Indic Languages
%A Nigam, Shubham
%A Sarkar, Suparnojit
%A Patel, Piyush
%Y Demner-Fushman, Dina
%Y Ananiadou, Sophia
%Y Roberts, Kirk
%Y Tsujii, Junichi
%S BioNLP 2026
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California
%@ 979-8-89176-434-7
%F nigam-etal-2026-indicmeddialog
%X We present 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 the MDDial corpus 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 introduced during automatic translation. Building on this dataset, we fine-tune IndicMedLM via parameter-efficient adaptation (LoRA) of a quantized small language model, incorporating an optional patient pre-context to personalise multi-turn symptom elicitation. We evaluate IndicMedLM against zero-shot multilingual baselines across ten languages and conduct systematic error analysis, identifying five failure modes: Instruction Drift, Label Collapse, Cross-Domain Confusion, Tokenization Failure, and Paraphrase-over-Label Generation. Results show strong post-processed diagnostic accuracy in Hindi, Marathi, and Bengali, while Assamese, Tamil, and Telugu remain in an extreme failure tier attributable to base-model tokenizer gaps, a finding with direct patient safety implications. Medical expert evaluation confirms the clinical plausibility and safety of the generated consultations.
%U https://aclanthology.org/2026.bionlp-1.84/
%P 1041-1055
Markdown (Informal)
[IndicMedDialog: A Parallel Multi-Turn Medical Dialogue Dataset for Accessible Healthcare in Indic Languages](https://aclanthology.org/2026.bionlp-1.84/) (Nigam et al., BioNLP 2026)
ACL