用不确定性检测动态决定是否调用外部知识，提升长文本问答效率。
To Retrieve or Not to Retrieve? Uncertainty Detection for Dynamic Retrieval Augmented Generation
- 根据模型不确定度判断是否调用检索，实现动态增强。
- 检索次数减少近一半，准确率仅轻微下降。
- 适合需要高效生成的长文本问答场景。
检索增强生成使大语言模型具备调用外部知识的能力，从而缓解幻觉问题。然而，以往方法多采用确定性检索，不适用于长文本问答等任务。本文提出通过动态检索——仅在模型缺乏必要知识时才调用——来提升效率。我们深入探讨了‘是否检索’的问题，评估了多种不确定性检测方法在长文本问答任务中的表现。结果表明，如度矩阵交集（Degree Matrix Jaccard）和离心率（Eccentricity）等检测指标可将检索调用次数减少近一半，同时仅带来轻微的准确率损失。
原文摘要 · Abstract (English)
Retrieval-Augmented Generation equips large language models with the capability to retrieve external knowledge, thereby mitigating hallucinations by incorporating information beyond the model's intrinsic abilities. However, most prior works have focused on invoking retrieval deterministically, which makes it unsuitable for tasks such as long-form question answering. Instead, dynamically performing retrieval by invoking it only when the underlying LLM lacks the required knowledge can be more efficient. In this context, we delve deeper into the question, "To Retrieve or Not to Retrieve?" by exploring multiple uncertainty detection methods. We evaluate these methods for the task of long-form question answering, employing dynamic retrieval, and present our comparisons. Our findings suggest that uncertainty detection metrics, such as Degree Matrix Jaccard and Eccentricity, can reduce the number of retrieval calls by almost half, with only a slight reduction in question-answering accuracy.
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。