生成式查询与文档扩展何时失效？跨方法、检索器与数据集的综合研究
When do Generative Query and Document Expansions Fail? A Comprehensive Study Across Methods, Retrievers, and Datasets
AI总结：
本文首次全面分析基于大语言模型的查询与文档扩展，发现扩展对弱检索器有益但对强检索器有害，并提出按模型强弱和数据集分布差异选择性使用扩展的实用建议。
摘要：
使用大语言模型（LMs）进行查询或文档扩展可以提升信息检索的泛化能力。然而，目前尚不清楚这些技术是普遍有益，还是仅在特定设置下有效，例如针对特定的检索模型、数据集领域或查询类型。为回答这一问题，我们开展了首个基于LM扩展的全面分析。我们发现，检索器性能与扩展带来的收益之间存在强负相关：扩展能提升较弱模型的得分，但通常会损害较强模型的表现。我们表明这一趋势在一组十一种扩展技术、十二个具有不同分布偏移的数据集以及二十四个检索模型上均成立。通过定性错误分析，我们推测：尽管扩展提供了额外信息（可能提升召回率），但它们也引入了额外噪声，使得难以区分排名靠前的相关文档（从而引入假阳性）。我们的结果建议如下方案：当使用较弱模型，或目标数据集在格式上与训练语料存在显著差异时，使用扩展；否则，避免使用扩展以保持相关性信号的清晰。
英文摘要：
Using large language models (LMs) for query or document expansion can improve generalization in information retrieval. However, it is unknown whether these techniques are universally beneficial or only effective in specific settings, such as for particular retrieval models, dataset domains, or query types. To answer this, we conduct the first comprehensive analysis of LM-based expansion. We find that there exists a strong negative correlation between retriever performance and gains from expansion: expansion improves scores for weaker models, but generally harms stronger models. We show this trend holds across a set of eleven expansion techniques, twelve datasets with diverse distribution shifts, and twenty-four retrieval models. Through qualitative error analysis, we hypothesize that although expansions provide extra information (potentially improving recall), they add additional noise that makes it difficult to discern between the top relevant documents (thus introducing false positives). Our results suggest the following recipe: use expansions for weaker models or when the target dataset significantly differs from training corpus in format; otherwise, avoid expansions to keep the relevance signal clear.
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。
