arXiv 2508.186732025-10-13cs.CLcs.AIcs.MM

均衡难度的定制化教学：通过提示课程提升多模态思维链的推理能力

Tailored Teaching with Balanced Difficulty: Elevating Reasoning in Multimodal Chain-of-Thought via Prompt Curriculum

Nanjing University of Aeronautics and Astronautics（南京航空航天大学）；Hunan Vanguard Group Corporation Co., Ltd.（湖南 Vanguard集团有限公司）；Huaneng Information Technology Co., Ltd.（华能信息技术有限公司）；Tsinghua University（清华大学）；Zhejiang University（浙江大学）；PowerChina Huadong Engineering Co., Ltd.（中国电建华东工程有限公司）

Xinglong Yang, Quan Feng, Zhongying Pan, Xiang Chen, Yu Tian, Wentong Li, Shuofei Qiao, Yuxia Geng, Xingyu Zhao, Sheng-Jun Huang

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文提出一种基于“均衡难度的定制化教学”原则的提示课程设计框架，通过结合模型感知难度和内在样本复杂性构建难度均衡的采样策略，有效提升了多模态大语言模型在多个基准上的推理性能并减少了随机采样导致的性能差异。

摘要：

多模态思维链（MCoT）提示的有效性通常受到随机或手动选择示例的限制。这些示例未能考虑模型特定的知识分布和任务的内在复杂性，导致模型性能次优且不稳定。为了解决这个问题，我们提出了一个受“均衡难度的定制化教学”教育原则启发的新框架。我们将提示选择重新构建为一个提示课程设计问题：构建一个与模型当前能力相匹配的有序训练示例集。我们的方法整合了两个互补信号：（1）模型感知的难度，通过在主动学习设置中的预测分歧来量化，捕捉模型自身认为具有挑战性的内容；（2）内在样本复杂性，独立于任何模型测量每个问题-图像对的固有难度。通过联合分析这些信号，我们开发了一种难度均衡的采样策略，确保所选提示示例在两个维度上都具有多样性。在五个具有挑战性的基准和多个流行的多模态大语言模型（MLLMs）上进行的广泛实验表明，我们的方法产生了实质且一致的改进，并大大减少了随机采样引起的性能差异，为增强多模态推理提供了一种有原则且稳健的方法。

英文摘要：

The effectiveness of Multimodal Chain-of-Thought (MCoT) prompting is often limited by the use of randomly or manually selected examples. These examples fail to account for both model-specific knowledge distributions and the intrinsic complexity of the tasks, resulting in suboptimal and unstable model performance. To address this, we propose a novel framework inspired by the pedagogical principle of "tailored teaching with balanced difficulty". We reframe prompt selection as a prompt curriculum design problem: constructing a well ordered set of training examples that align with the model's current capabilities. Our approach integrates two complementary signals: (1) model-perceived difficulty, quantified through prediction disagreement in an active learning setup, capturing what the model itself finds challenging; and (2) intrinsic sample complexity, which measures the inherent difficulty of each question-image pair independently of any model. By jointly analyzing these signals, we develop a difficulty-balanced sampling strategy that ensures the selected prompt examples are diverse across both dimensions. Extensive experiments conducted on five challenging benchmarks and multiple popular Multimodal Large Language Models (MLLMs) demonstrate that our method yields substantial and consistent improvements and greatly reduces performance discrepancies caused by random sampling, providing a principled and robust approach for enhancing multimodal reasoning.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。