Detecting insomnia from clinical narratives requires both accurate classification and clinically grounded reasoning with interpretable evidence. We present our systems for the SMM4H-HeaRD 2026 shared task, which leverages MIMIC-III notes annotated with rule-based insomnia criteria and supporting evidence spans. We explore two complementary approaches: parameter-efficient fine-tuning of lightweight models using QLoRA and LoRA, and few-shot prompting of large language models for joint reasoning and evidence extraction. Our best system achieves an F1-score of 0.7333 on binary classification and a micro-F1 of 0.6535 on multi-label rule prediction, with up to 0.5192 partial-match F1 for evidence extraction. Results show that lightweight fine-tuned models can outperform larger models in classification, while larger models demonstrate stronger reasoning but struggle with precise span localization, highlighting a key gap in clinically interpretable NLP systems.

This paper describes a production minded multilingual system built for the NLP-AI4Health shared task, designed to produce concise, medically accurate summaries and patient friendly answers for Head and Neck Cancer (HNC) and Blood Donation. We finetune Gemma2-2B under a strict model size constraint (<3B parameters) using parameter efficient adaptation (LoRA) and practical engineering to handle long dialogues, code mixing, and multilingual scripts. The pipeline couples careful preprocessing, token aware chunking, and constrained decoding with lightweight retrieval and verification steps. We report per language quantitative metrics and provide an analysis of design choices and operational considerations for real world deployment.