arXiv 2504.101982025-05-17cs.CL

DioR：面向动态检索增强生成的自适应认知检测与上下文检索优化

DioR: Adaptive Cognitive Detection and Contextual Retrieval Optimization for Dynamic Retrieval-Augmented Generation

Zhejiang Key Laboratory of Intelligent Education Technology and Application, Zhejiang Normal University（浙江智能教育技术与应用重点实验室，浙江师范大学）；School of Computer Science and Technology, Zhejiang Normal University（浙江师范大学计算机科学与技术学院）；School of Computer Science and Engineering, Southeast University（东南大学计算机科学与工程学院）；Department of Computer Science and Engineering, Hong Kong University of Science and Technology（香港科技大学计算机科学与工程系）；School of Computer Science and Technology, Soochow University（苏州大学计算机科学与技术学院）

Hanghui Guo, Jia Zhu, Shimin Di, Weijie Shi, Zhangze Chen, Jiajie Xu

备注：: Accepted to ACL2025 Main

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

针对现有动态RAG方法存在的检索触发机制不足、检索内容缺乏审查的问题，提出包含自适应认知检测与上下文检索优化组件的DioR方法，在所有任务上性能更优。

摘要：

动态检索增强生成（RAG）已在缓解大语言模型（LLM）生成过程中的幻觉问题上取得显著成效。然而，现有动态RAG方法在两个关键方面存在明显局限：1）缺乏有效的检索触发控制机制；2）缺乏对检索内容的有效审查。为解决这些局限，我们提出一种创新的动态RAG方法——DioR（自适应认知检测与上下文检索优化），它包含自适应认知检测和上下文检索优化两个核心组件，专门用于判断大语言模型何时需要检索、检索哪些内容有用。实验结果表明，DioR在所有任务上均取得了更优性能，证明了本研究的有效性。

英文摘要：

Dynamic Retrieval-augmented Generation (RAG) has shown great success in mitigating hallucinations in large language models (LLMs) during generation. However, existing dynamic RAG methods face significant limitations in two key aspects: 1) Lack of an effective mechanism to control retrieval triggers, and 2) Lack of effective scrutiny of retrieval content. To address these limitations, we propose an innovative dynamic RAG method, DioR (Adaptive Cognitive Detection and Contextual Retrieval Optimization), which consists of two main components: adaptive cognitive detection and contextual retrieval optimization, specifically designed to determine when retrieval is needed and what to retrieve for LLMs is useful. Experimental results demonstrate that DioR achieves superior performance on all tasks, demonstrating the effectiveness of our work.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。