@inproceedings{zechariah-etal-2025-patient,
title = "Patient-Centric Question Answering- Overview of the Shared Task at the Second Workshop on {NLP} and {AI} for Multilingual and Healthcare Communication",
author = "Zechariah, Arun and
Krishna, Balu and
Mary Thomas, Hannah and
Mammen, Joy and
Misra Sharma, Dipti and
Krishnamurthy, Parameswari and
Mujadia, Vandan and
Dasari, Priyanka and
Arjunaswamy, Vishnuraj",
editor = "Krishnamurthy, Parameswari and
Mujadia, Vandan and
Misra Sharma, Dipti and
Mary Thomas, Hannah",
booktitle = "NLP-AI4Health",
month = dec,
year = "2025",
address = "Mumbai, India",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.nlpai4health-main.5/",
pages = "55--68",
ISBN = "979-8-89176-315-9",
abstract = "This paper presents an overview of the Shared Task on Patient-Centric Question Answering, organized as part of the NLP-AI4Health workshop at IJCNLP. The task aims to bridge the digital divide in healthcare by developing inclusive systems for two critical domains: Head and Neck Cancer (HNC) and Cystic Fibrosis (CF). We introduce the NLP4Health-2025 Dataset, a novel, large-scale multilingual corpus consisting of more than 45,000 validated multi-turn dialogues between patients and healthcare providers across 10 languages: Assamese, Bangla, Dogri, English, Gujarati, Hindi, Kannada, Marathi, Tamil, and Telugu. Participants were challenged to develop lightweight models ($<$ 3 billion parameters) to perform two core activities: (1) Clinical Summarization, encompassing both abstractive summaries and structured clinical extraction (SCE), and (2) Patient-Centric QA, generating empathetic, factually accurate answers in the dialogue native language. This paper details the hybrid human-agent dataset construction pipeline, task definitions, evaluation metrics, and analyzes the performance of 9 submissions from 6 teams. The results demonstrate the viability of small language models (SLMs) in low-resource medical settings when optimized via techniques like LoRA and RAG."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zechariah-etal-2025-patient">
<titleInfo>
<title>Patient-Centric Question Answering- Overview of the Shared Task at the Second Workshop on NLP and AI for Multilingual and Healthcare Communication</title>
</titleInfo>
<name type="personal">
<namePart type="given">Arun</namePart>
<namePart type="family">Zechariah</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Balu</namePart>
<namePart type="family">Krishna</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hannah</namePart>
<namePart type="family">Mary Thomas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joy</namePart>
<namePart type="family">Mammen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dipti</namePart>
<namePart type="family">Misra Sharma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Parameswari</namePart>
<namePart type="family">Krishnamurthy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vandan</namePart>
<namePart type="family">Mujadia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Priyanka</namePart>
<namePart type="family">Dasari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vishnuraj</namePart>
<namePart type="family">Arjunaswamy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>NLP-AI4Health</title>
</titleInfo>
<name type="personal">
<namePart type="given">Parameswari</namePart>
<namePart type="family">Krishnamurthy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vandan</namePart>
<namePart type="family">Mujadia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dipti</namePart>
<namePart type="family">Misra Sharma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hannah</namePart>
<namePart type="family">Mary Thomas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Mumbai, India</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-315-9</identifier>
</relatedItem>
<abstract>This paper presents an overview of the Shared Task on Patient-Centric Question Answering, organized as part of the NLP-AI4Health workshop at IJCNLP. The task aims to bridge the digital divide in healthcare by developing inclusive systems for two critical domains: Head and Neck Cancer (HNC) and Cystic Fibrosis (CF). We introduce the NLP4Health-2025 Dataset, a novel, large-scale multilingual corpus consisting of more than 45,000 validated multi-turn dialogues between patients and healthcare providers across 10 languages: Assamese, Bangla, Dogri, English, Gujarati, Hindi, Kannada, Marathi, Tamil, and Telugu. Participants were challenged to develop lightweight models (< 3 billion parameters) to perform two core activities: (1) Clinical Summarization, encompassing both abstractive summaries and structured clinical extraction (SCE), and (2) Patient-Centric QA, generating empathetic, factually accurate answers in the dialogue native language. This paper details the hybrid human-agent dataset construction pipeline, task definitions, evaluation metrics, and analyzes the performance of 9 submissions from 6 teams. The results demonstrate the viability of small language models (SLMs) in low-resource medical settings when optimized via techniques like LoRA and RAG.</abstract>
<identifier type="citekey">zechariah-etal-2025-patient</identifier>
<location>
<url>https://aclanthology.org/2025.nlpai4health-main.5/</url>
</location>
<part>
<date>2025-12</date>
<extent unit="page">
<start>55</start>
<end>68</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Patient-Centric Question Answering- Overview of the Shared Task at the Second Workshop on NLP and AI for Multilingual and Healthcare Communication
%A Zechariah, Arun
%A Krishna, Balu
%A Mary Thomas, Hannah
%A Mammen, Joy
%A Misra Sharma, Dipti
%A Krishnamurthy, Parameswari
%A Mujadia, Vandan
%A Dasari, Priyanka
%A Arjunaswamy, Vishnuraj
%Y Krishnamurthy, Parameswari
%Y Mujadia, Vandan
%Y Misra Sharma, Dipti
%Y Mary Thomas, Hannah
%S NLP-AI4Health
%D 2025
%8 December
%I Association for Computational Linguistics
%C Mumbai, India
%@ 979-8-89176-315-9
%F zechariah-etal-2025-patient
%X This paper presents an overview of the Shared Task on Patient-Centric Question Answering, organized as part of the NLP-AI4Health workshop at IJCNLP. The task aims to bridge the digital divide in healthcare by developing inclusive systems for two critical domains: Head and Neck Cancer (HNC) and Cystic Fibrosis (CF). We introduce the NLP4Health-2025 Dataset, a novel, large-scale multilingual corpus consisting of more than 45,000 validated multi-turn dialogues between patients and healthcare providers across 10 languages: Assamese, Bangla, Dogri, English, Gujarati, Hindi, Kannada, Marathi, Tamil, and Telugu. Participants were challenged to develop lightweight models (< 3 billion parameters) to perform two core activities: (1) Clinical Summarization, encompassing both abstractive summaries and structured clinical extraction (SCE), and (2) Patient-Centric QA, generating empathetic, factually accurate answers in the dialogue native language. This paper details the hybrid human-agent dataset construction pipeline, task definitions, evaluation metrics, and analyzes the performance of 9 submissions from 6 teams. The results demonstrate the viability of small language models (SLMs) in low-resource medical settings when optimized via techniques like LoRA and RAG.
%U https://aclanthology.org/2025.nlpai4health-main.5/
%P 55-68
Markdown (Informal)
[Patient-Centric Question Answering- Overview of the Shared Task at the Second Workshop on NLP and AI for Multilingual and Healthcare Communication](https://aclanthology.org/2025.nlpai4health-main.5/) (Zechariah et al., NLP-AI4Health 2025)
ACL
- Arun Zechariah, Balu Krishna, Hannah Mary Thomas, Joy Mammen, Dipti Misra Sharma, Parameswari Krishnamurthy, Vandan Mujadia, Priyanka Dasari, and Vishnuraj Arjunaswamy. 2025. Patient-Centric Question Answering- Overview of the Shared Task at the Second Workshop on NLP and AI for Multilingual and Healthcare Communication. In NLP-AI4Health, pages 55–68, Mumbai, India. Association for Computational Linguistics.