Saved in:
Bibliographic Details
Main Authors: Elshaer, Ziad, Rashed, Essam A.
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2510.14353
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909849761087488
author Elshaer, Ziad
Rashed, Essam A.
author_facet Elshaer, Ziad
Rashed, Essam A.
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2510_14353
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle CURE: Confidence-driven Unified Reasoning Ensemble Framework for Medical Question Answering
Elshaer, Ziad
Rashed, Essam A.
Computation and Language
Artificial Intelligence
Medical Physics
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.
title CURE: Confidence-driven Unified Reasoning Ensemble Framework for Medical Question Answering
topic Computation and Language
Artificial Intelligence
Medical Physics
url https://arxiv.org/abs/2510.14353