用不确定性估计提升检索效率，比复杂管道更省力还靠谱
Adaptive Retrieval Without Self-Knowledge? Bringing Uncertainty Back Home
- 用不确定性估计替代复杂检索流程，降低计算开销
- 在6个数据集上，精度与主流方法相当但速度更快
- 适合追求高效且稳定生成的开发者和研究者
检索增强生成（RAG）能提升大语言模型问答准确率并缓解幻觉问题，但显著增加计算成本。此外，RAG并非总必要，可能引入无关信息。近期自适应检索方法尝试融合语言模型内在知识与外部信息，依赖模型自我认知，但常忽略效率评估及与不确定性估计技术的对比。本文通过全面分析35种自适应检索方法——包括8种新方法和27种不确定性估计技术——在6个数据集上使用10项指标评估问答性能、自我知识和效率。结果表明，不确定性估计技术在效率和自我知识方面通常优于复杂流水线，同时保持相当的问答表现。
原文摘要 · Abstract (English)
Retrieval Augmented Generation (RAG) improves correctness of Question Answering (QA) and addresses hallucinations in Large Language Models (LLMs), yet greatly increase computational costs. Besides, RAG is not always needed as may introduce irrelevant information. Recent adaptive retrieval methods integrate LLMs' intrinsic knowledge with external information appealing to LLM self-knowledge, but they often neglect efficiency evaluations and comparisons with uncertainty estimation techniques. We bridge this gap by conducting a comprehensive analysis of 35 adaptive retrieval methods, including 8 recent approaches and 27 uncertainty estimation techniques, across 6 datasets using 10 metrics for QA performance, self-knowledge, and efficiency. Our findings show that uncertainty estimation techniques often outperform complex pipelines in terms of efficiency and self-knowledge, while maintaining comparable QA performance.
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。