自适应LLM-符号推理：通过动态逻辑求解器组合
Adaptive LLM-Symbolic Reasoning via Dynamic Logical Solver Composition
AI总结：
提出自适应神经符号推理框架，动态识别策略并选择逻辑求解器，性能超越GPT-4o和DeepSeek-V3.1，并提升纯LLM方法。
摘要：
神经符号自然语言处理方法旨在利用大型语言模型和形式逻辑求解器的互补优势。然而，当前方法大多是静态的，即目标求解器的集成在设计时预先确定，这阻碍了采用多样化形式推理策略的能力。为解决这一问题，我们引入了一个自适应、多范式的神经符号推理框架，该框架：（1）从自然语言表达的问题中自动识别形式推理策略；（2）通过自动形式化接口动态选择并应用专门的形式逻辑求解器。在单项和多项范式推理任务上的广泛实验支持以下结论：LLM在预测必要的形式推理策略方面是有效的，准确率超过90%。这使得与形式逻辑求解器的灵活集成成为可能，从而使我们的框架在性能上分别比GPT-4o和DeepSeek-V3.1等竞争基线高出27%和6%。此外，自适应推理甚至能对纯LLM方法产生积极影响，在GPT-4o的零样本、思维链和符号思维链设置中分别带来10%、5%和6%的提升。最后，尽管较小的模型在自适应神经符号推理中面临困难，但后训练提供了一条可行的改进路径。总体而言，这项工作为自适应LLM-符号推理奠定了基础，为在异构推理挑战上统一材料推理和形式推理提供了一条前进之路。
英文摘要：
Neuro-symbolic NLP methods aim to leverage the complementary strengths of large language models and formal logical solvers. However, current approaches are mostly static in nature, i.e., the integration of a target solver is predetermined at design time, hindering the ability to employ diverse formal inference strategies. To address this, we introduce an adaptive, multi-paradigm, neuro-symbolic inference framework that: (1) automatically identifies formal reasoning strategies from problems expressed in natural language; and (2) dynamically selects and applies specialized formal logical solvers via autoformalization interfaces. Extensive experiments on individual and multi-paradigm reasoning tasks support the following conclusions: LLMs are effective at predicting the necessary formal reasoning strategies with an accuracy above 90 percent. This enables flexible integration with formal logical solvers, resulting in our framework outperforming competing baselines by 27 percent and 6 percent compared to GPT-4o and DeepSeek-V3.1, respectively. Moreover, adaptive reasoning can even positively impact pure LLM methods, yielding gains of 10, 5, and 6 percent on zero-shot, CoT, and symbolic CoT settings with GPT-4o. Finally, although smaller models struggle with adaptive neuro-symbolic reasoning, post-training offers a viable path to improvement. Overall, this work establishes the foundations for adaptive LLM-symbolic reasoning, offering a path forward for unifying material and formal inferences on heterogeneous reasoning challenges.
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。
