超越被动批判性思维：培养主动提问以增强人机协作
Beyond Passive Critical Thinking: Fostering Proactive Questioning to Enhance Human-AI Collaboration
AI总结：
本研究提出主动批判性思维范式，构建GSM-MC与GSM-MCE基准评估模型主动提问能力，发现现有模型表现不佳，通过改进强化学习算法将Qwen3-1.7B准确率从0.15%提升至73.98%，助力人机协作优化。
摘要：
批判性思维对于构建鲁棒的AI系统至关重要，可防止其盲目接受有缺陷的数据或存在偏差的推理。然而，此前的研究主要聚焦于被动批判性思维——模型仅拒绝有问题的查询，而未采取建设性措施来满足用户需求。本研究提出主动批判性思维范式，模型会主动向用户询问缺失或待澄清的信息，以更好地解决用户查询。\n为评估该能力，我们基于GSM8K构建了两个新型基准GSM-MC和GSM-MCE，用于评估不完整或误导性条件下的数学推理能力。GSM-MC包含1368道数学题，每道题被刻意移除一个关键变量，要求模型识别并请求缺失信息；GSM-MCE进一步引入无关细节提升难度，以测试抗干扰鲁棒性。\n在Qwen3和Llama系列模型上的实验表明，尽管这些模型经大量后训练和推理时扩展在传统推理任务中表现优异，但在主动批判性思维上表现不佳，小模型尤其明显。不过我们证明强化学习（RL）可显著提升该能力：使用我们改进的RL算法，Qwen3-1.7B在GSM-MC上的准确率从0.15%提升至73.98%。我们希望本研究能推动模型通过主动批判性思维，在问题解决中与用户开展更有效的协作。
英文摘要：
Critical thinking is essential for building robust AI systems, preventing them from blindly accepting flawed data or biased reasoning. However, prior work has primarily focused on passive critical thinking, where models simply reject problematic queries without taking constructive steps to address user requests. In this work, we introduce proactive critical thinking, a paradigm where models actively seek missing or clarifying information from users to resolve their queries better. To evaluate this capability, we present GSM-MC and GSM-MCE, two novel benchmarks based on GSM8K for assessing mathematical reasoning under incomplete or misleading conditions. GSM-MC contains 1,368 math problems with a key variable deliberately removed, requiring models to identify and request the missing information. GSM-MCE further increases the difficulty by introducing irrelevant details to test robustness against distractions. Experiments on Qwen3 and Llama series models show that, while these models excel in traditional reasoning tasks due to extensive post-training and inference-time scaling, they struggle with proactive critical thinking, especially smaller ones. However, we demonstrate that reinforcement learning (RL) can significantly improve this ability. Using our enhanced RL algorithm, we achieve substantial gains, boosting the Qwen3-1.7B's accuracy from 0.15% to 73.98% on GSM-MC. We hope this work advances models that collaborate more effectively with users in problem-solving through proactive critical thinking.
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。
