提出逻辑完备框架Aristotle，提升大模型逻辑推理准确率与效率
Aristotle: Mastering Logical Reasoning with A Logic-Complete Decompose-Search-Resolve Framework
- 将符号表达与逻辑规则融入分解-搜索-求解全流程
- 在多个数据集上超越现有方法，复杂逻辑任务表现更优
- 适合需要高精度逻辑推理的AI研究者与开发者
大型语言模型在各类推理任务中已取得显著进展，但在逻辑推理方面仍面临效能与效率双重挑战。根源在于现有系统未能充分利用逻辑任务的内在结构，贯穿于分解、搜索与求解过程。为此，我们提出逻辑完备推理框架Aristotle，包含三个核心组件：逻辑分解器、逻辑搜索路由器和逻辑求解器。该框架将符号表达与逻辑规则全面集成至整个推理流程，显著缓解逻辑推理瓶颈，即降低子任务复杂度、减少搜索错误、解决逻辑矛盾。实验结果表明，Aristotle在多个数据集上持续优于当前最优推理框架，在复杂逻辑推理场景中尤为突出。代码将于https://llm-symbol.github.io/Aristotle/ 开源。
原文摘要 · Abstract (English)
In the context of large language models (LLMs), current advanced reasoning methods have made impressive strides in various reasoning tasks. However, when it comes to logical reasoning tasks, major challenges remain in both efficacy and efficiency. This is rooted in the fact that these systems fail to fully leverage the inherent structure of logical tasks throughout the reasoning processes such as decomposition, search, and resolution. To address this, we propose a logic-complete reasoning framework, Aristotle, with three key components: Logical Decomposer, Logical Search Router, and Logical Resolver. In our framework, symbolic expressions and logical rules are comprehensively integrated into the entire reasoning process, significantly alleviating the bottlenecks of logical reasoning, i.e., reducing sub-task complexity, minimizing search errors, and resolving logical contradictions. The experimental results on several datasets demonstrate that Aristotle consistently outperforms state-of-the-art reasoning frameworks in both accuracy and efficiency, particularly excelling in complex logical reasoning scenarios. We will open-source all our code at https://llm-symbol.github.io/Aristotle/.
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。