DiLA：利用差分逻辑层增强大语言模型的工具学习能力
DiLA: Enhancing LLM Tool Learning with Differential Logic Layer
AI总结：
本文提出DiLA方法，通过将差分逻辑层与LLM结合，把逻辑约束融入网络前向与反向传播，由LLM生成初始解、逻辑层迭代细化，从而在SAT和图着色等推理问题上提升LLM的逻辑推理能力并优于现有方法。
摘要：
考虑到大语言模型（LLMs）在逻辑推理与规划方面面临的挑战，先前的工作试图通过让LLMs访问外部求解器来增强其能力。尽管在简单推理问题上已取得进展，但求解经典的约束满足问题（如布尔可满足性问题（SAT）和图着色问题（GCP））对现成求解器而言仍然困难，因为这些问题具有复杂的表达式和指数级的搜索空间。在本文中，我们提出了一种新颖的差分逻辑层辅助语言建模（DiLA）方法，其中逻辑约束被整合到网络层的前向和后向传播过程中，为LLM工具学习提供了另一种选择。在DiLA中，LLM旨在将语言描述转换为逻辑约束并识别质量最高的初始解，而差分逻辑层则专注于迭代地细化由LLM提示得到的解。利用逻辑层作为桥梁，DiLA增强了LLM在一系列由布尔变量编码的推理问题上的逻辑推理能力，保证了求解过程的效率和正确性。我们在两个经典推理问题上评估了DiLA的性能，并通过实验证明其持续优于现有的基于提示的方法和求解器辅助的方法。
英文摘要：
Considering the challenges faced by large language models (LLMs) in logical reasoning and planning, prior efforts have sought to augment LLMs with access to external solvers. While progress has been made on simple reasoning problems, solving classical constraint satisfaction problems, such as the Boolean Satisfiability Problem (SAT) and Graph Coloring Problem (GCP), remains difficult for off-the-shelf solvers due to their intricate expressions and exponential search spaces. In this paper, we propose a novel differential logic layer-aided language modeling (DiLA) approach, where logical constraints are integrated into the forward and backward passes of a network layer, to provide another option for LLM tool learning. In DiLA, LLM aims to transform the language description to logic constraints and identify initial solutions of the highest quality, while the differential logic layer focuses on iteratively refining the LLM-prompted solution. Leveraging the logic layer as a bridge, DiLA enhances the logical reasoning ability of LLMs on a range of reasoning problems encoded by Boolean variables, guaranteeing the efficiency and correctness of the solution process. We evaluate the performance of DiLA on two classic reasoning problems and empirically demonstrate its consistent outperformance against existing prompt-based and solver-aided approaches.
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。
