KAG-Thinker：通过知识增强生成实现大语言模型的交互式思考与深度推理
KAG-Thinker: Interactive Thinking and Deep Reasoning in LLMs via Knowledge-Augmented Generation
- Inclusion AI Ant Group（Inclusion AI蚂蚁集团）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
本文提出KAG-Thinker框架，通过轻量级LLM驱动的多轮交互思考与深度推理，将复杂问题分解为子问题并分类检索与推理，利用知识边界与深度求解模块增强逻辑连贯性与知识获取。
AI中文摘要：
本文介绍了KAG-Thinker，它将KAG升级为一个由轻量级大语言模型（LLM）驱动的多轮交互式思考与深度推理框架。该方法为解决复杂问题构建了结构化的思考过程，增强了LLM在特定领域知识库（KBs）问答（Q&A）任务中推理过程的逻辑连贯性与上下文一致性。遵循KAG基于逻辑形式引导的检索与推理技术路线，该框架首先通过广度分解将复杂问题分解为可独立求解的子问题（也称为逻辑形式）。每个逻辑形式以自然语言和逻辑函数两种等价形式表示，随后被分类为知识检索或推理分析任务。这些任务间的依赖关系与参数传递通过逻辑函数接口进行显式建模。在求解过程中，Retrieval函数执行检索任务，检索指定知识单元的单跳结构化与非结构化信息；Math和Deduce函数则用于执行推理分析任务。其次值得注意的是，在知识检索子问题任务中，LLM与外部知识源被视为等价的知识库。我们使用知识边界模块，通过置信度校准和反思推理等自我调节机制来确定最优来源，并使用深度求解模块来增强知识获取的全面性……
英文摘要：
In this paper, we introduce KAG-Thinker, which upgrade KAG to a multi-turn interactive thinking and deep reasoning framework powered by a dedicated parameter-light large language model (LLM). Our approach constructs a structured thinking process for solving complex problems, enhancing the the logical coherence and contextual consistency of the reasoning process in question-answering (Q&A) tasks on domain-specific knowledge bases (KBs) within LLMs. Following the \textbf{Logical Form} guided retrieval and reasoning technology route of KAG, this framework first decomposes complex questions into independently solvable sub-problems (which are also referred to as logical forms) through \textbf{breadth decomposition}. Each such logical form is represented in two equivalent forms-natural language and logical function-and subsequently classified as either a Knowledge Retrieval or Reasoning Analysis task. Dependencies and parameter passing between these tasks are explicitly modeled via logical function interfaces. In the solving process, the Retrieval function performs retrieval tasks. It retrieves one-hop structured and unstructured information of specified knowledge unit. While the Math and Deduce functions are used to perform reasoning analysis tasks. Secondly, it is worth noting that, in the Knowledge Retrieval sub-problem tasks, LLMs and external knowledge sources are regarded as equivalent KBs. We use the \textbf{knowledge boundary} module to determine the optimal source using self-regulatory mechanisms such as confidence calibration and reflective reasoning, and use the \textbf{depth solving} module to enhance the comprehensiveness of knowledge acquisition...
