让大模型学会识别自己不知道，提升判断准确率。
Linking Perception, Confidence and Accuracy in MLLMs
- 用信心驱动强化学习，让模型更敏感地感知视觉信息。
- 在四个数据集上实现8.8%的稳定性能提升。
- 适合需要可靠判断的场景，如医疗、自动驾驶等。
多模态大模型（MLLMs）近年聚焦于提升视觉感知以增强准确性，但一个关键问题未被解答：模型是否知道自己不知道？通过探测实验，我们发现现有模型存在严重的信心误校准问题。为此，提出信心驱动强化学习（CDRL），利用原始噪声图像对和基于信心的奖励机制，提升感知敏感性并校准模型信心。训练之外，校准后的信心可直接用于测试时扩展，带来免费增益。进一步提出信心感知测试时扩展（CA-TTS），由专家模型动态协调自一致、自反思与视觉自检模块，并提供外部验证。集成框架在四个基准上均取得新最优结果，性能稳定提升8.8%。消融实验证明各模块有效性及扩展优势。
原文摘要 · Abstract (English)
Recent advances in Multi-modal Large Language Models (MLLMs) have predominantly focused on enhancing visual perception to improve accuracy. However, a critical question remains unexplored: Do models know when they do not know? Through a probing experiment, we reveal a severe confidence miscalibration problem in MLLMs. To address this, we propose Confidence-Driven Reinforcement Learning (CDRL), which uses original-noise image pairs and a novel confidence-based reward to enhance perceptual sensitivity and robustly calibrate the model's confidence. Beyond training benefits, calibrated confidence enables more effective test-time scaling as a free lunch. We further propose Confidence-Aware Test-Time Scaling (CA-TTS), which dynamically coordinates Self-Consistency, Self-Reflection, and Visual Self-Check modules guided by confidence signals. An Expert Model acts in multiple roles (e.g., Planner, Critic, Voter) to schedule these modules and provide external verification. Our integrated framework establishes new state-of-the-art results with consistent 8.8% gains across four benchmarks. More ablation studies demonstrate the effectiveness of each module and scaling superiority.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。