mlsanityData to 14 Oct 2026

CURE: Confidence-driven Unified Reasoning Ensemble Framework for Medical Question Answering

arXiv 2510.14353 ↗First posted 16 Oct 2025cs.CL cs.AI physics.med-phcited by 0

On the map: LLM reasoning → Clinical and biomedical applications

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Clinical and biomedical applications, one of 17 directions in LLM reasoning. Builds on 19 of its 40 references that are in the map. First posted on arXiv 16 Oct 2025.

Builds on

19 of 40 references.

Closest ancestors · 1

Same direction, newest first

  1. 2025MedicalAgentsBench for Complex Medical Reasoning: Comparing Internalized Reasoning Models versus Externalized Agent-based Frameworks10 Mar

Other references · 18

  1. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,132
  2. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,708
  3. 2024Gemma 2: Improving Open Language Models at a Practical Sizecited by 1,998
  4. 2019PubMedQA: A Dataset for Biomedical Research Question Answeringcited by 1,288
  5. 2023Capabilities of GPT-4 on Medical Challenge Problemscited by 638
  6. 2023LLM-Blender: Ensembling Large Language Models with Pairwise Ranking and Generative Fusioncited by 564
  7. 2024Mixture-of-Agents Enhances Large Language Model Capabilitiescited by 438
  8. 2025MedGemma Technical Reportcited by 436
  9. 2023Towards Expert-Level Medical Question Answering with Large Language Modelscited by 384
  10. 2023MEDITRON-70B: Scaling Medical Pretraining for Large Language Modelscited by 274
  11. 2025MedXpertQA: Benchmarking Expert-Level Medical Reasoning and Understandingcited by 224
  12. 2023HuatuoGPT, towards Taming Language Model to Be a Doctorcited by 214
6 more
  1. 2023Large Language Model Routing with Benchmark Datasetscited by 172
  2. 2023DoctorGLM: Fine-tuning your Chinese Doctor is not a Herculean Taskcited by 131
  3. 2024LLM-MedQA: Enhancing Medical Question Answering through Case Studies in Large Language Modelscited by 32
  4. 2024MedQA-CS: Objective Structured Clinical Examination (OSCE)-Style Benchmark for Evaluating LLM Clinical Skillscited by 17
  5. 2024MEG: Medical Knowledge-Augmented Large Language Models for Question Answeringcited by 6
  6. 2025On the Performance of an Explainable Language Model on PubMedQAcited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Collaboration among Multiple Large Language Models for Medical Question Answering
  2. 2026A Multi-Agent Framework for Medical AI: Leveraging Fine-Tuned GPT, LLaMA, and DeepSeek R1 for Evidence-Based and Bias-Aware Clinical Query Processing
  3. 2025Trustworthy Medical Question Answering: An Evaluation-Centric Survey
  4. 2026ReGraM: Region-First Knowledge Graph Reasoning for Medical Question Answering
  5. 2026Let LLMs Judge Each Other: Multi-Agent Peer-Reviewed Reasoning for Medical Question Answering
  6. 2026Knowing When to Abstain: Medical LLMs Under Clinical Uncertainty
  7. 2026MedRouter: Demystifying Knowledge Differences Across Medical LLMs for Routing-Based Reasoning
  8. 2025Med-U1: Incentivizing Unified Medical Reasoning in LLMs via Large-scale Reinforcement Learning