把信息抽取当记忆库，提升大模型推理准确率
IE as Cache: Information Extraction Enhanced Agentic Reasoning
- 用查询驱动提取+缓存感知推理，动态维护中间信息
- 多任务基准测试中推理准确率显著提升
- 适合需要长期记忆的复杂推理场景
信息抽取旨在从非结构化文本中提炼出对决策有重要意义的结构化信息，是下游理解与推理的基础。然而，传统方法将其视为终点：提取后的结构常被孤立使用，而非在多步推理中持续维护和复用。本文提出「IE-as-Cache」框架，将信息抽取重新定位为认知缓存，以增强智能体推理能力。受分层计算机内存启发，该方法结合查询驱动的信息提取与缓存感知推理，动态维护紧凑的中间信息并过滤噪声。在多种大模型和挑战性基准上的实验表明，推理准确率显著提升，证明信息抽取可作为可复用的认知资源，为未来信息抽取的下游应用提供新方向。
原文摘要 · Abstract (English)
Information Extraction aims to distill structured, decision-relevant information from unstructured text, serving as a foundation for downstream understanding and reasoning. However, it is traditionally treated merely as a terminal objective: once extracted, the resulting structure is often consumed in isolation rather than maintained and reused during multi-step inference. Moving beyond this, we propose \textit{IE-as-Cache}, a framework that repurposes IE as a cognitive cache to enhance agentic reasoning. Drawing inspiration from hierarchical computer memory, our approach combines query-driven extraction with cache-aware reasoning to dynamically maintain compact intermediate information and filter noise. Experiments on challenging benchmarks across diverse LLMs demonstrate significant improvements in reasoning accuracy, indicating that IE can be effectively repurposed as a reusable cognitive resource and offering a promising direction for future research on downstream uses of IE.
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。