用零样本答案嗅觉重排文档，显著提升问答检索准确率
ASRank: Zero-Shot Re-Ranking with Answer Scent for Document Retrieval
- 利用大模型计算文档答案与问题嗅觉的匹配度进行重排序
- 在NQ数据集上Top-1准确率从19.2%提升至46.5%
- 无需微调，适用于多种检索场景，适合构建高效问答系统
检索增强生成（RAG）模型在开放域问答中备受关注，其效果依赖于前几篇检索文档的质量。然而，传统检索方法常无法将最相关文档排在前列。本文提出ASRank，一种基于零样本答案嗅觉的重排序方法，利用预训练大模型计算文档生成答案与问题答案嗅觉的一致性得分。该方法在多个数据集（NQ、TriviaQA、WebQA、ArchivalQA、HotpotQA、Entity Questions）上表现优异。特别地，对于MSS，NQ数据集的Top-1检索准确率从19.2%提升至46.5%；对于BM25，从22.1%提升至47.3%。相较于先进方法（如基于BM25的UPR，Top-1为35.4%），ASRank达到47.3%的领先性能。
原文摘要 · Abstract (English)
Retrieval-Augmented Generation (RAG) models have drawn considerable attention in modern open-domain question answering. The effectiveness of RAG depends on the quality of the top retrieved documents. However, conventional retrieval methods sometimes fail to rank the most relevant documents at the top. In this paper, we introduce ASRank, a new re-ranking method based on scoring retrieved documents using zero-shot answer scent which relies on a pre-trained large language model to compute the likelihood of the document-derived answers aligning with the answer scent. Our approach demonstrates marked improvements across several datasets, including NQ, TriviaQA, WebQA, ArchivalQA, HotpotQA, and Entity Questions. Notably, ASRank increases Top-1 retrieval accuracy on NQ from $19.2\%$ to $46.5\%$ for MSS and $22.1\%$ to $47.3\%$ for BM25. It also shows strong retrieval performance on several datasets compared to state-of-the-art methods (47.3 Top-1 by ASRank vs 35.4 by UPR by BM25).
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。