DioR让大模型更智能地决定何时检索、检什么，减少幻觉。
DioR: Adaptive Cognitive Detection and Contextual Retrieval Optimization for Dynamic Retrieval-Augmented Generation
- 通过自适应认知检测判断何时需要检索
- 通过上下文优化筛选出更相关的内容
- 适合需要高可靠性的问答与生成场景
动态检索增强生成（Dynamic RAG）在缓解大语言模型（LLMs）生成过程中的幻觉问题方面表现优异。然而，现有动态RAG方法在两个关键方面存在显著局限：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。为解决这些问题，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），包含两个核心组件：自适应认知检测和上下文检索优化，专门用于确定大语言模型何时需要检索以及应检索什么内容。实验结果表明，DioR在所有任务上均取得更优性能，验证了该方法的有效性。
原文摘要 · Abstract (English)
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.
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。