{"ID":2854465,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.14353","arxiv_id":"2510.14353","title":"CURE: Confidence-driven Unified Reasoning Ensemble Framework for Medical Question Answering","abstract":"High-performing medical Large Language Models (LLMs) typically require extensive fine-tuning with substantial computational resources, limiting accessibility for resource-constrained healthcare institutions. This study introduces a confidence-driven multi-model framework that leverages model diversity to enhance medical question answering without fine-tuning. Our framework employs a two-stage architecture: a confidence detection module assesses the primary model's certainty, and an adaptive routing mechanism directs low-confidence queries to Helper models with complementary knowledge for collaborative reasoning. We evaluate our approach using Qwen3-30B-A3B-Instruct, Phi-4 14B, and Gemma 2 12B across three medical benchmarks; MedQA, MedMCQA, and PubMedQA. Result demonstrate that our framework achieves competitive performance, with particularly strong results in PubMedQA (95.0\\%) and MedMCQA (78.0\\%). Ablation studies confirm that confidence-aware routing combined with multi-model collaboration substantially outperforms single-model approaches and uniform reasoning strategies. This work establishes that strategic model collaboration offers a practical, computationally efficient pathway to improve medical AI systems, with significant implications for democratizing access to advanced medical AI in resource-limited settings.","short_abstract":"High-performing medical Large Language Models (LLMs) typically require extensive fine-tuning with substantial computational resources, limiting accessibility for resource-constrained healthcare institutions. This study introduces a confidence-driven multi-model framework that leverages model diversity to enhance medica...","url_abs":"https://arxiv.org/abs/2510.14353","url_pdf":"https://arxiv.org/pdf/2510.14353v1","authors":"[\"Ziad Elshaer\",\"Essam A. Rashed\"]","published":"2025-10-16T06:46:11Z","proceeding":"cs.CL","tasks":"[\"cs.CL\",\"cs.AI\",\"physics.med-ph\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false}