Co-Evolving Structured Knowledge and Reasoning in Language Models

2026-08-26

AI Summary

为解决检索增强方法引入无关上下文和结构化知识库构建昂贵的问题，提出KBevo框架，联合学习构建和推理结构化知识库，提高问答准确性。

Abstract

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.

Problem

• Structured Knowledge
• Reasoning
• Language Models
• Knowledge Base
• Question Answering

Innovation

• Co-Evolving Framework
• Structured Knowledge Base
• End-to-End Optimization
• QA Outcome Rewards
• Compositional Factual Reasoning