让大模型学会自适应推理，避免机械套用记忆模式。
AdaR: A Framework for Equipping LLMs with Adaptive Reasoning
- 通过变换变量自动生成逻辑等价问题，引导模型建立正确推理关联。
- 在数学推理任务上显著提升表现，且仅需少量数据即可训练。
- 适合希望提升大模型推理鲁棒性的研究者与开发者使用。
数学推理是衡量大语言模型智能水平的重要指标。然而现有模型在鲁棒性和泛化能力方面存在不足，其根源在于虚假推理——即推理过程受表面相关性驱动，导致模型盲目复现训练数据中的记忆模式。为此，本文提出AdaR框架，使大模型具备自适应推理能力，建立查询模板与推理过程间的正确关联。AdaR通过改变变量值自动合成逻辑等价问题，并利用可验证奖励的强化学习（RLVR）进行训练，惩罚虚假逻辑，鼓励自适应逻辑。为保障数据质量，从原始问题中提取解题逻辑，通过代码执行获得答案，并进行合理性校验。实验表明，AdaR在数学推理任务上实现显著提升，同时保持高数据效率。即使先进大模型仍存在鲁棒性与泛化缺陷，本方法亦能有效缓解。项目代码已开源：https://github.com/NJUNLP/AdaR。
原文摘要 · Abstract (English)
Mathematical reasoning is a primary indicator of large language models (LLMs) intelligence. However, existing LLMs exhibit failures in robustness and generalization. This paper attributes these deficiencies to spurious reasoning, wherein generated reasoning traces are driven by superficial correlations, leading models to blindly reproduce memorized patterns from the training data. To address this challenge, we propose the AdaR framework to equip LLMs with adaptive reasoning, wherein models establish correct correlations between query templates and reasoning processes. AdaR automatically synthesizes logically equivalent queries by varying variable values and trains models using Reinforcement Learning with Verifiable Rewards (RLVR) to penalize spurious logic while encouraging adaptive logic. To ensure data quality, we extract the problem-solving logic from the original query, generate the corresponding answer through code execution, and then apply a sanity check. Experimental results demonstrate that AdaR achieves substantial improvements in mathematical reasoning while maintaining high data efficiency. Furthermore, even advanced LLMs still exhibit deficiencies in robustness and generalization, which our work effectively mitigates. Our project is available at https://github.com/NJUNLP/AdaR.
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。