MedMind AI at #SMM4H-HeaRD 2026: Data Extraction and Generation Using Prompt Engineering and Structured Outputs (Tasks 1–6)

Aatish Pradhan, Brian M. Habersberger


Abstract
Six tasks from the SMM4H–HeaRD 2026 workshop were addressed with task-specific large-language-model (LLM) pipelines relying on prompt engineering, strict structured (JSON) responses, and deterministic rule sets. The pipelines utilize no task-specific fine-tuning and can be adapted across diverse clinical and social media data. This study demonstrates that general-purpose LLMs (gpt-5.4-mini and gpt-5.4) can accurately extract and classify crucial health information when constrained by strict output schemas. Notably, our hybrid approachachieved the best overall performance among all participating systems for Task 2 (Insomnia Detection).
Anthology ID:
2026.smm4h-1.31
Volume:
Proceedings of the 11th Social Media Mining for Health Research and Applications (SMM4H-HeaRD 2026) Workshop and Shared Tasks
Month:
July
Year:
2026
Address:
San Diego, United States
Editors:
Guillermo Lopez-Garcia, Graciela Gonzalez-Hernandez
Venues:
SMM4H | WS
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
187–205
Language:
URL:
https://preview.aclanthology.org/ingest-acl-workshops/2026.smm4h-1.31/
DOI:
Bibkey:
Cite (ACL):
Aatish Pradhan and Brian M. Habersberger. 2026. MedMind AI at #SMM4H-HeaRD 2026: Data Extraction and Generation Using Prompt Engineering and Structured Outputs (Tasks 1–6). In Proceedings of the 11th Social Media Mining for Health Research and Applications (SMM4H-HeaRD 2026) Workshop and Shared Tasks, pages 187–205, San Diego, United States. Association for Computational Linguistics.
Cite (Informal):
MedMind AI at #SMM4H-HeaRD 2026: Data Extraction and Generation Using Prompt Engineering and Structured Outputs (Tasks 1–6) (Pradhan & Habersberger, SMM4H 2026)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingest-acl-workshops/2026.smm4h-1.31.pdf