利用相關反饋嵌入進行零樣本密集檢索

Zero-Shot Dense Retrieval with Embeddings from Relevance Feedback

October 28, 2024

作者: Nour Jedidi, Yung-Sung Chuang, Leslie Shing, James Glass

cs.AI

摘要

在沒有相關監督的情況下，建立有效的密集檢索系統仍然困難。最近的研究試圖克服這一挑戰，方法是利用大型語言模型（LLM）生成假設文件，以尋找最接近的真實文件。然而，這種方法僅依賴LLM具有與查詢相關的領域特定知識，這可能並不實際。此外，生成假設文件可能效率低下，因為它需要LLM為每個查詢生成大量標記。為了應對這些挑戰，我們引入了來自相關反饋的真實文件嵌入（ReDE-RF）。受到相關反饋的啟發，ReDE-RF提議將假設文件生成重新定義為一個相關性估計任務，使用LLM選擇應該用於最近鄰搜索的文件。通過這種重新定義，LLM不再需要領域特定知識，只需要判斷什麼是相關的。此外，相關性估計只需要LLM輸出單個標記，從而提高搜索延遲。我們的實驗表明，ReDE-RF在廣泛的低資源檢索數據集上始終優於最先進的零樣本密集檢索方法，同時在每個查詢的延遲方面也取得了顯著改進。

English

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.