@inproceedings{sriram-sahoo-2026-midas,
title = "{MIDAS}{\_}{SYNUR} at {MEDIQA}-{SYNUR} 2026: A Prompting Study for Clinical Observation Extraction from Nurse Dictation Transcriptions",
author = "Sriram, Swetha Krishna and
Sahoo, Akshitaa",
editor = "Ben Abacha, Asma and
Bethard, Steven and
Bitterman, Danielle and
Naumann, Tristan and
Roberts, Kirk",
booktitle = "Proceedings of the 8th Workshop on Clinical Natural Language Processing (Clinical {NLP}) @ {LREC} 2026",
month = may,
year = "2026",
address = "Palma, Mallorca (Spain)",
publisher = "ELRA Language Resources Association (ELRA)",
url = "https://aclanthology.org/2026.clinicalnlp-1.27/",
doi = "10.63317/4h7qk3596z83",
pages = "244--250",
abstract = "This paper describes MIDAS{\_}SYNUR, a system developed for the MEDIQA-SYNUR task at ClinicalNLP 2026 on observation extraction from nurse dictations. The primary system adopts a single-prompt, field-rich few-shot strategy using GPT-5.2, jointly generating all schema fields in one structured output. Few-shot demonstrations are curated and grouped by value type, with five examples per type, promoting consistency across heterogeneous value distributions while leveraging global context to resolve cross-field dependencies. To analyze design trade-offs, this holistic strategy is compared against a field-wise decomposed prompting baseline, where each schema field is extracted independently using explicit positive and NULL demonstrations to improve absence detection and reduce cross-field interference. Zero-shot variants of both approaches are also evaluated to isolate the contribution of in-context examples. The results highlight inference-time prompting as a simple, reproducible, and competitive baseline for large-scale clinical observation extraction from conversational nurse dictations. Keywords: Prompt Engineering, Few-Shot Prompting, In-Context Learning, Structured Output"
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sriram-sahoo-2026-midas">
<titleInfo>
<title>MIDAS_SYNUR at MEDIQA-SYNUR 2026: A Prompting Study for Clinical Observation Extraction from Nurse Dictation Transcriptions</title>
</titleInfo>
<name type="personal">
<namePart type="given">Swetha</namePart>
<namePart type="given">Krishna</namePart>
<namePart type="family">Sriram</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Akshitaa</namePart>
<namePart type="family">Sahoo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 8th Workshop on Clinical Natural Language Processing (Clinical NLP) @ LREC 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Asma</namePart>
<namePart type="family">Ben Abacha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Bethard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Danielle</namePart>
<namePart type="family">Bitterman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tristan</namePart>
<namePart type="family">Naumann</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>
<originInfo>
<publisher>ELRA Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Palma, Mallorca (Spain)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper describes MIDAS_SYNUR, a system developed for the MEDIQA-SYNUR task at ClinicalNLP 2026 on observation extraction from nurse dictations. The primary system adopts a single-prompt, field-rich few-shot strategy using GPT-5.2, jointly generating all schema fields in one structured output. Few-shot demonstrations are curated and grouped by value type, with five examples per type, promoting consistency across heterogeneous value distributions while leveraging global context to resolve cross-field dependencies. To analyze design trade-offs, this holistic strategy is compared against a field-wise decomposed prompting baseline, where each schema field is extracted independently using explicit positive and NULL demonstrations to improve absence detection and reduce cross-field interference. Zero-shot variants of both approaches are also evaluated to isolate the contribution of in-context examples. The results highlight inference-time prompting as a simple, reproducible, and competitive baseline for large-scale clinical observation extraction from conversational nurse dictations. Keywords: Prompt Engineering, Few-Shot Prompting, In-Context Learning, Structured Output</abstract>
<identifier type="citekey">sriram-sahoo-2026-midas</identifier>
<identifier type="doi">10.63317/4h7qk3596z83</identifier>
<location>
<url>https://aclanthology.org/2026.clinicalnlp-1.27/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>244</start>
<end>250</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MIDAS_SYNUR at MEDIQA-SYNUR 2026: A Prompting Study for Clinical Observation Extraction from Nurse Dictation Transcriptions
%A Sriram, Swetha Krishna
%A Sahoo, Akshitaa
%Y Ben Abacha, Asma
%Y Bethard, Steven
%Y Bitterman, Danielle
%Y Naumann, Tristan
%Y Roberts, Kirk
%S Proceedings of the 8th Workshop on Clinical Natural Language Processing (Clinical NLP) @ LREC 2026
%D 2026
%8 May
%I ELRA Language Resources Association (ELRA)
%C Palma, Mallorca (Spain)
%F sriram-sahoo-2026-midas
%X This paper describes MIDAS_SYNUR, a system developed for the MEDIQA-SYNUR task at ClinicalNLP 2026 on observation extraction from nurse dictations. The primary system adopts a single-prompt, field-rich few-shot strategy using GPT-5.2, jointly generating all schema fields in one structured output. Few-shot demonstrations are curated and grouped by value type, with five examples per type, promoting consistency across heterogeneous value distributions while leveraging global context to resolve cross-field dependencies. To analyze design trade-offs, this holistic strategy is compared against a field-wise decomposed prompting baseline, where each schema field is extracted independently using explicit positive and NULL demonstrations to improve absence detection and reduce cross-field interference. Zero-shot variants of both approaches are also evaluated to isolate the contribution of in-context examples. The results highlight inference-time prompting as a simple, reproducible, and competitive baseline for large-scale clinical observation extraction from conversational nurse dictations. Keywords: Prompt Engineering, Few-Shot Prompting, In-Context Learning, Structured Output
%R 10.63317/4h7qk3596z83
%U https://aclanthology.org/2026.clinicalnlp-1.27/
%U https://doi.org/10.63317/4h7qk3596z83
%P 244-250
Markdown (Informal)
[MIDAS_SYNUR at MEDIQA-SYNUR 2026: A Prompting Study for Clinical Observation Extraction from Nurse Dictation Transcriptions](https://aclanthology.org/2026.clinicalnlp-1.27/) (Sriram & Sahoo, ClinicalNLP 2026)
ACL