KBM：为大语言模型的自适应检索划定知识边界
KBM: Delineating Knowledge Boundary for Adaptive Retrieval in Large Language Models
AI总结：
本文提出知识边界模型（KBM），通过表达LLM对给定问题的已知/未知状态来决定是否触发检索增强生成（RAG），在11个中英文数据集及多种复杂场景下有效划定了知识边界，显著降低了实现最佳端到端性能所需的检索比例。
摘要：
大型语言模型（LLM）通常难以应对动态变化的知识以及处理未知的静态信息。检索增强生成（RAG）被用于应对这些挑战，并在提升LLM性能方面具有显著影响。事实上，我们发现并非所有问题都需要触发RAG。通过仅检索LLM未知的知识部分，并允许LLM回答其余部分，我们可以有效降低时间和计算成本。在我们的工作中，我们提出了一种知识边界模型（KBM），用于表达给定问题的已知/未知状态，并确定是否需要触发RAG。在11个英文和中文数据集上进行的实验表明，KBM有效地划定了知识边界，显著减少了实现最佳端到端性能所需的检索比例。此外，我们还在三种复杂场景下评估了KBM的有效性：动态知识、长尾静态知识和多跳问题，以及其作为外部LLM插件的功能。
英文摘要：
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.
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。
