扩展推理，失去控制：评估大型推理模型中的指令遵循能力
Scaling Reasoning, Losing Control: Evaluating Instruction Following in Large Reasoning Models
AI总结：
本研究提出MathIF基准，发现推理能力增强与指令遵循之间存在张力，长思维链或推理强化学习会降低遵循能力，简单干预可部分恢复但牺牲推理性能。
摘要：
指令遵循对于将大型语言模型（LLMs）与用户意图对齐至关重要。尽管近期面向推理的模型在复杂数学问题上表现出色，但它们遵循自然语言指令的能力仍未得到充分探索。在本工作中，我们引入了MathIF，一个专门用于评估数学推理任务中指令遵循能力的基准。我们的实证分析揭示了扩展推理能力与保持可控性之间持续存在的张力，因为推理更有效的模型往往难以遵循用户指令。我们发现，经过蒸馏长思维链微调或使用面向推理的强化学习训练的模型，其指令遵循能力常常下降，尤其是在生成长度增加时。此外，我们表明，即使简单的干预措施也能部分恢复服从性，但以牺牲推理性能为代价。这些发现凸显了当前LLM训练范式中的根本张力，并激励了对更具指令感知能力的推理模型的需求。我们在https://github.com/TingchenFu/MathIF发布了代码和数据。
英文摘要：
Instruction-following is essential for aligning large language models (LLMs) with user intent. While recent reasoning-oriented models exhibit impressive performance on complex mathematical problems, their ability to adhere to natural language instructions remains underexplored. In this work, we introduce MathIF, a dedicated benchmark for evaluating instruction-following in mathematical reasoning tasks. Our empirical analysis reveals a consistent tension between scaling up reasoning capacity and maintaining controllability, as models that reason more effectively often struggle to comply with user directives. We find that models tuned on distilled long chains-of-thought or trained with reasoning-oriented reinforcement learning often degrade in instruction adherence, especially when generation length increases. Furthermore, we show that even simple interventions can partially recover obedience, though at the cost of reasoning performance. These findings highlight a fundamental tension in current LLM training paradigms and motivate the need for more instruction-aware reasoning models. We release the code and data at https://github.com/TingchenFu/MathIF.
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。
