让语言模型一边构建知识库一边推理，自动优化问答效果。
Co-Evolving Structured Knowledge and Reasoning in Language Models
- 边问答边构建结构化知识库，双向优化提升质量。
- 知识库更大更连通，答案可及性提高37%以上。
- 适合需要高准确性和可控性的复杂问答任务。
检索增强方法通过将语言模型与外部知识结合来提升事实准确性，但基于非结构化文本的检索常引入无关上下文，且难以控制检索内容。结构化知识库虽更具可控性，但构建成本高且推理能力脆弱。为此，我们提出KBevo：一种联合学习构建结构化知识库并基于其进行推理的协同演化框架。通过以问答结果奖励端到端优化两个组件，推理成功可直接提升知识库质量。该方法生成更大、更连通的知识结构，显著提升答案可及性，同时在组合式事实推理和可控性上优于标准检索基线。
原文摘要 · Abstract (English)
Retrieval-augmented methods improve factual accuracy by grounding language models in external knowledge, but retrieving over unstructured text often introduces irrelevant context and offers limited control over the retrieved information. Structured knowledge bases offer a more controllable alternative, yet they are expensive to construct and often brittle to reason over. To address these limitations, we propose KBevo: a co-evolving framework that jointly learns to construct a structured knowledge base and reason over it for knowledge-intensive question answering. By optimizing both components end-to-end with QA outcome rewards, our method enables reasoning success to directly improve the quality of the constructed knowledge base. This leads to larger, better-connected knowledge structures with higher answer reachability, while also improving compositional factual reasoning and controllability compared to standard retrieval baselines.
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。