发现大模型逻辑推理会突然崩溃，提出新训练方法缓解此问题。
Logical Phase Transitions: Understanding Collapse in LLM Logical Reasoning
- 通过控制逻辑复杂度，发现推理性能在临界点突然下降。
- 在5个基准上提升平均准确率，最高增益达+3.95。
- 适合关注大模型可靠性与可解释性的研究者。
符号逻辑推理是大语言模型的关键能力，对数学推理和法律判断等高风险领域具有重要意义。本文系统分析了逻辑复杂度逐步增加时的推理表现，首次揭示了一种新现象——逻辑相变：推理性能并非平滑退化，而是在某一临界逻辑深度前保持稳定，之后突然崩溃，类似物理相变中水在临界温度冻结。基于此，我们提出神经符号课程微调框架，通过自适应对齐自然语言与逻辑符号，构建共享表征，并围绕相变边界重塑训练动态，逐步增强模型在更高逻辑深度下的推理能力。在5个基准上的实验表明，该方法有效缓解了高复杂度下的推理崩溃，相比零样本提示平均提升1.26分，思维链（CoT）下提升3.95分，同时增强了对未见逻辑组合的泛化能力。代码与数据已公开于https://github.com/AI4SS/Logical-Phase-Transitions。
原文摘要 · Abstract (English)
Symbolic logical reasoning is a critical yet underexplored capability of large language models (LLMs), providing reliable and verifiable decision-making in high-stakes domains such as mathematical reasoning and legal judgment. In this study, we present a systematic analysis of logical reasoning under controlled increases in logical complexity, and reveal a previously unrecognized phenomenon, which we term Logical Phase Transitions: rather than degrading smoothly, logical reasoning performance remains stable within a regime but collapses abruptly beyond a critical logical depth, mirroring physical phase transitions such as water freezing beyond a critical temperature threshold. Building on this insight, we propose Neuro-Symbolic Curriculum Tuning, a principled framework that adaptively aligns natural language with logical symbols to establish a shared representation, and reshapes training dynamics around phase-transition boundaries to progressively strengthen reasoning at increasing logical depths. Experiments on five benchmarks show that our approach effectively mitigates logical reasoning collapse at high complexity, yielding average accuracy gains of +1.26 in naive prompting and +3.95 in CoT, while improving generalization to unseen logical compositions. Code and data are available at https://github.com/AI4SS/Logical-Phase-Transitions.
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。