用图形化认知结构提升大模型逻辑推理能力
Towards a Neurosymbolic Reasoning System Grounded in Schematic Representations
- 将图像图式作为认知基础，构建可执行的符号化推理程序
- 在逻辑推理任务中显著提升准确性与可解释性
- 适合需要可靠推理和透明决策的研究者使用
尽管自然语言理解取得显著进展，大型语言模型（LLMs）在逻辑推理方面仍易出错，缺乏人类般的稳健心智表征。我们提出原型神经符号系统Embodied-LM，将理解与逻辑推理基于图像图式（image schemas）——源自感官运动经验的重复模式，构成人类认知的基础结构。系统通过答案集编程（Answer Set Programming）实现声明式空间推理，形式化这些认知结构。在逻辑推断任务上的评估表明，LLMs可通过具身认知结构被引导理解场景，这些结构可被形式化为可执行程序，且生成的表征支持有效推理并增强可解释性。当前实现聚焦于空间原语，但已建立引入更复杂动态表征的计算基础。
原文摘要 · Abstract (English)
Despite significant progress in natural language understanding, Large Language Models (LLMs) remain error-prone when performing logical reasoning, often lacking the robust mental representations that enable human-like comprehension. We introduce a prototype neurosymbolic system, Embodied-LM, that grounds understanding and logical reasoning in schematic representations based on image schemas-recurring patterns derived from sensorimotor experience that structure human cognition. Our system operationalizes the spatial foundations of these cognitive structures using declarative spatial reasoning within Answer Set Programming. Through evaluation on logical deduction problems, we demonstrate that LLMs can be guided to interpret scenarios through embodied cognitive structures, that these structures can be formalized as executable programs, and that the resulting representations support effective logical reasoning with enhanced interpretability. While our current implementation focuses on spatial primitives, it establishes the computational foundation for incorporating more complex and dynamic representations.
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。