发表机构
Cornell University（康奈尔大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对检索增强方法的局限，提出协同演化框架KBevo，联合学习构建结构化知识库与推理，提升了知识结构质量、答案可达性及推理与可控性。
AI 中文摘要
检索增强方法通过将语言模型与外部知识绑定来提升事实准确性，但对非结构化文本进行检索常引入无关上下文，且对检索信息的控制能力有限。结构化知识库提供了更可控的替代方案，但其构建成本高昂且推理时易失效。为解决这些局限，我们提出KBevo：一种协同演化框架，联合学习构建结构化知识库并针对知识密集型问答任务进行推理。通过用问答结果奖励端到端优化两个组件，我们的方法使推理成功能直接提升所构建知识库的质量，进而形成更大、连接性更好的知识结构，拥有更高的答案可达性，同时相比标准检索基线，还提升了组合事实推理能力与可控性。
英文摘要
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.
CommentsAccepted to COLM 2026. Code available at https://github.com/kilian-group/KBevo
