你的语言模型可能思考过于僵化：通过对称增强训练实现推理一致性
Your Language Model May Think Too Rigidly: Achieving Reasoning Consistency with Symmetry-Enhanced Training
AI总结：
针对查询措辞变化导致LLM推理性能下降的问题，提出对称增强数据增强方法MEND，在知识提取阶段提升鲁棒性，实验证明其在逻辑和算术推理任务上表现更优。
摘要：
大型语言模型（LLMs）在各种任务中展现了强大的推理能力。然而，即使查询措辞的微小变化，尽管保留了底层语义含义，也可能显著影响其性能。为了解决这个问题，我们专注于增强LLMs对查询变化中对称性的感知，并提出了对称增强（MEND）数据增强方法，这是一种以数据为中心的方法，旨在提高模型从上下文中提取有用信息的能力。与现有强调推理链增强的方法不同，我们的方法通过查询增强在知识提取阶段提高模型的鲁棒性，从而实现更高效的数据训练和对分布外（OOD）设置更强的泛化能力。在逻辑和算术推理任务上的大量实验表明，MEND在多种查询变化下增强了推理性能，为通过结构化数据集整理来提高LLM鲁棒性提供了新的见解。
英文摘要：
Large Language Models (LLMs) have demonstrated strong reasoning capabilities across various tasks. However, even minor variations in query phrasing, despite preserving the underlying semantic meaning, can significantly affect their performance. To address this, we focus on enhancing LLMs' awareness of symmetry in query variations and propose syMmetry-ENhanceD (MEND) Data Augmentation, a data-centric approach that improves the model's ability to extract useful information from context. Unlike existing methods that emphasize reasoning chain augmentation, our approach improves model robustness at the knowledge extraction stage through query augmentations, enabling more data-efficient training and stronger generalization to Out-of-Distribution (OOD) settings. Extensive experiments on both logical and arithmetic reasoning tasks show that MEND enhances reasoning performance across diverse query variations, providing new insight into improving LLM robustness through structured dataset curation.
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。
