提出知识边界模型，让大模型自动判断何时该查资料，省时省钱。
KBM: Delineating Knowledge Boundary for Adaptive Retrieval in Large Language Models
- 用知识边界模型判断问题是否需调用外部检索
- 在11个数据集上降低约40%的检索次数
- 适合处理动态知识、冷门信息等复杂场景
大语言模型常面临知识动态变化和静态未知信息的挑战。检索增强生成（RAG）虽能缓解此问题，但并非所有问题都需检索。本文提出知识边界模型（KBM），用于判断给定问题中哪些知识是模型已知的，哪些未知，从而决定是否触发RAG。实验在11个中英文数据集上验证，KBM可有效划定知识边界，显著减少达到最优端到端性能所需的检索比例。此外，我们在动态知识、长尾静态知识及多跳推理三种复杂场景下评估其有效性，并验证其作为外部插件的通用性。
原文摘要 · Abstract (English)
Large Language Models (LLMs) often struggle with dynamically changing knowledge and handling unknown static information. Retrieval-Augmented Generation (RAG) is employed to tackle these challenges and has a significant impact on improving LLM performance. In fact, we find that not all questions need to trigger RAG. By retrieving parts of knowledge unknown to the LLM and allowing the LLM to answer the rest, we can effectively reduce both time and computational costs. In our work, we propose a Knowledge Boundary Model (KBM) to express the known/unknown of a given question, and to determine whether a RAG needs to be triggered. Experiments conducted on 11 English and Chinese datasets illustrate that the KBM effectively delineates the knowledge boundary, significantly decreasing the proportion of retrievals required for optimal end-to-end performance. Furthermore, we evaluate the effectiveness of KBM in three complex scenarios: dynamic knowledge, long-tail static knowledge, and multi-hop problems, as well as its functionality as an external LLM plug-in.
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。