发现共享的逻辑子空间：通过自然语言和符号视角的对齐来引导LLM逻辑推理
Discovering a Shared Logical Subspace: Steering LLM Logical Reasoning via Alignment of Natural-Language and Symbolic Views
AI总结：
本文提出通过对齐自然语言和符号视角的逻辑子空间来提升LLM的多步逻辑推理能力，通过实验验证该方法在四个基准测试中提升了准确率并具备良好的泛化能力。
摘要：
大型语言模型（LLMs）在多步逻辑推理上仍存在困难。现有方法或仅优化自然语言推理链，或附加符号求解器作为外部模块。本文提出是否LLM内部存在一个共享的逻辑子空间，能够同时对齐自然语言和符号语言的推理视角。我们的假设是该逻辑子空间捕捉了LLM中跨视角共享的逻辑推理能力，同时独立于表层形式。为验证此假设，我们利用对齐分析在自然语言和符号语言推理链的残差激活上学习低维子空间，以最大跨视角相关性。此外，我们设计了一种无需训练的方法，引导LLM推理链沿此逻辑子空间，从而利用两种视角的互补推理信号。在四个逻辑推理基准测试中的实验表明，我们的方法有效，提升了准确率高达11个百分点，并在跨领域问题上表现良好。
英文摘要：
Large Language Models (LLMs) still struggle with multi-step logical reasoning. Existing approaches either purely refine the reasoning chain in natural language form or attach a symbolic solver as an external module. In this work, we instead ask whether LLMs contain a shared internal logical subspace that simultaneously aligns natural-language and symbolic-language views of the reasoning process. Our hypothesis is that this logical subspace captures logical reasoning capabilities in LLMs that are shared across views while remaining independent of surface forms. To verify this, we employ Canonical Correlation Analysis on the paired residual activations from natural-language and symbolic-language reasoning chains, learning a low-dimensional subspace with maximum cross-view correlation. Furthermore, we design a training-free approach that steers LLMs reasoning chain along this logical subspace, thereby leveraging the complementary reasoning signals from both views. Experiments on four logical reasoning benchmarks demonstrate the effectiveness of our approach, improving accuracy by up to 11 percentage points and generalizing well on out-of-domain problems.
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。
