This paper describes the submission by Team Aurum to the CL4Health @ LREC 2026 Shared Task on Case Report Form (CRF) Filling from dyspnea patient clinical notes. Extracting 134 structured clinical fields using a single Large Language Model (LLM) call often leads to schema-following errors, hallucination, and poor attention over complex instructions. To address this, we propose a modular extraction pipeline built with DSPy, which decomposes the 134 CRF fields into 14 specialized, domain-specific extractors (e.g., Medical History, Lab Values, Acute Diagnoses). We conducted extensive experiments across multiple multilingual LLMs, including Llama4 Maverik, GPT-4o, GPT-4o Mini, DeepSeek-V3, Gemma-3-12B-Instruct, and Qwen-series models. Among these, Qwen3-Max (Thinking) with our optimized v2 prompts achieved the best performance on the development set with a Macro-F1 of 0.70, outperforming other evaluated models such as GPT-4o (0.68) and DeepSeek-V3 (0.66). Prompt optimization resulted in measurable gains, improving Qwen3-Max performance from 0.67 to 0.70. Using this configuration, our pipeline achieved an official Codabench Test Macro-F1 score of 0.68 in English and 0.67 in Italian, securing the 1st place ranking overall in the shared task.

This paper describes the system submitted by team Aurum to the Medical Decision Extraction, Analysis, and Classification Task (MedExACT) at BioNLP 2026. The task requires the extraction and classification of contiguous text spans representing medical decisions from lengthy ICU discharge summaries. To address the dual challenges of long document lengths and severe class imbalance withina limited training set of 350 notes, we propose a two-pronged strategy. First, we employ a tripartite data augmentation pipeline utilizing rule-based entity replacement, LLM-based contextual paraphrasing, and synthetic note generation to expand the training data to over 2,300 notes. Second, we fine-tune a domain-specific Clinical Longformer model equipped with a sliding-window inference mechanism and Focal Loss to handle sequences up to 2,048 tokens while focusing on rare decision categories. Paired with a targeted post-processing module,our system achieved a Final Score of 0.5251, demonstrating high token-level detection (Token F1: 0.6311) and strong stability across patient demographics.

This study addresses the Shared Task on Patient-Centric Multilingual Question Answering, which focuses on generating summaries and patient-oriented answers from multi-turn medical dialogues related to Head and Neck Cancer and Cystic Fibrosis across ten languages. The Qwen3-1.7B model is fine-tuned using QLoRA for three tasks—Summarization, Question Answering, and Information Extraction—while updating only approximately 1.6% of parameters through task-specific adapter layers. The resulting system demonstrates strong semantic fidelity, as evidenced by high BERTScore and COMET scores, particularly for Kannada, English, Telugu, and Tamil, with comparatively lower performance in Assamese, Bangla, Gujarati, and Marathi. The modular fine-tuning design enables efficient task adaptation while satisfying the constraints on model size and computational resources.