AutoIndex：為檢索學習表徵程序

摘要

我們提出AutoIndex，這是一個用於學習表示程式的框架：可執行的轉換，將原始文檔映射到檢索系統所暴露的表示。不同於調整檢索器、重新排序器或一小組預處理超參數，AutoIndex在索引之前搜尋對文檔進行切片、豐富、正規化、重新加權或重新組織的程式。在每次迭代中，AutoIndex執行驗證引導的程式搜尋，其中智能體診斷當前程式的失敗並合成候選更新，僅保留在結果索引下能提升檢索品質的更新。我們在CRUMB（一個異質檢索任務基準）上評估AutoIndex，所有實驗皆固定使用BM25。學習到的程式在所有8個任務上，相較於靜態全文BM25基準，均提升了召回率，平均Recall@100提升8.4%，nDCG@10提升8.3%，最大提升分別為Recall@100提升30.5%，nDCG@10提升43.6%。這些結果表明，文檔表示不應被視為檢索開始前的固定預處理選擇，而應作為明確的優化目標。可重現我們結果的程式碼已於https://github.com/auto-index/autoindex公開。

English

We present AutoIndex, a framework for learning representation programs: executable transformations that map raw documents into the representations exposed to a retrieval system. Rather than tuning retrievers, rerankers, or a small set of preprocessing hyperparameters, AutoIndex searches over programs that slice, enrich, normalize, reweight, or reorganize documents before indexing. At each iteration, AutoIndex performs validation-guided program search, in which agents diagnose failures of the current program and synthesize candidate updates, retaining only updates that improve retrieval quality under the resulting index. We evaluate AutoIndex on CRUMB, a benchmark of heterogeneous retrieval tasks, with BM25 held fixed across all experiments. The learned programs improve recall over a static full-document BM25 baseline on all 8 tasks, with average gains of +8.4% in Recall@100 and +8.3% in nDCG@10, and largest gains of +30.5% in Recall@100 and +43.6% in nDCG@10. These results suggest that document representation should not be treated as a fixed preprocessing choice made before retrieval begins, but as an explicit optimization target. Code to reproduce our results is available at https://github.com/auto-index/autoindex.