利用来自相关性反馈的嵌入进行零样本密集检索
Zero-Shot Dense Retrieval with Embeddings from Relevance Feedback
AI总结：
本文提出 ReDE-RF，将 LLM 生成假设文档改为相关性估计并选取真实文档生成嵌入，在低资源零样本密集检索中提升准确率与查询延迟。
摘要：
在缺乏相关性监督的情况下，构建有效的密集检索系统仍然十分困难。近期研究试图通过使用大型语言模型（LLM）生成假设性文档来克服这一挑战，这些假设性文档可用于寻找最接近的真实文档。然而，这种方法完全依赖 LLM 具备与查询相关的特定领域知识，而这可能并不现实。此外，生成假设性文档可能效率低下，因为它要求 LLM 为每个查询生成大量 token。为应对这些挑战，我们提出了 Real Document Embeddings from Relevance Feedback（ReDE-RF，基于相关性反馈的真实文档嵌入）。受相关性反馈启发，ReDE-RF 建议将假设性文档生成重新构建为相关性估计任务，使用 LLM 来选择哪些文档应当用于最近邻搜索。通过这种重构，LLM 不再需要特定领域知识，而只需判断什么是相关的。此外，相关性估计只要求 LLM 输出单个 token，从而改善搜索延迟。我们的实验表明，ReDE-RF 在广泛的低资源检索数据集上持续超越最先进的零样本密集检索方法，同时在每查询延迟方面也取得了显著改进。
英文摘要：
Building effective dense retrieval systems remains difficult when relevance supervision is not available. Recent work has looked to overcome this challenge by using a Large Language Model (LLM) to generate hypothetical documents that can be used to find the closest real document. However, this approach relies solely on the LLM to have domain-specific knowledge relevant to the query, which may not be practical. Furthermore, generating hypothetical documents can be inefficient as it requires the LLM to generate a large number of tokens for each query. To address these challenges, we introduce Real Document Embeddings from Relevance Feedback (ReDE-RF). Inspired by relevance feedback, ReDE-RF proposes to re-frame hypothetical document generation as a relevance estimation task, using an LLM to select which documents should be used for nearest neighbor search. Through this re-framing, the LLM no longer needs domain-specific knowledge but only needs to judge what is relevant. Additionally, relevance estimation only requires the LLM to output a single token, thereby improving search latency. Our experiments show that ReDE-RF consistently surpasses state-of-the-art zero-shot dense retrieval methods across a wide range of low-resource retrieval datasets while also making significant improvements in latency per-query.
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。
