让检索结果反哺查询扩展，提升搜索准确性
ADORE: Iterative Query Expansion with Retrieval-Grounded Relevance Feedback
- 通过迭代式反馈机制，用检索结果指导查询扩展
- 在BEIR上比最强基线提升3.6%，在BRIGHT上提升9.2%
- 适合需要精准检索的问答与信息获取场景
基于大模型的查询扩展可通过补充上下文提升检索效果。然而，多数方法仍依赖生成式扩写，缺乏对目标语料库响应的验证，易引入检索偏差、放大误导性词汇或遗漏关键区分词。本文提出ADORE（ADapt, Observe, Relevance Evaluate）框架，将检索结果作为反馈用于下一轮扩展。每轮中，大模型生成伪段落，检索器返回相关文档，相关性评估器判断其与原查询的匹配程度，从而识别应强化、未覆盖和应抑制的内容。在TREC Deep Learning、BEIR和BRIGHT三个数据集上，ADORE持续优于强基线，在BEIR上平均nDCG@10比BM25提升24.5%，比最优查询扩展方法提升3.6%；在BRIGHT上分别提升122.9%和9.2%。代码与数据已公开。
原文摘要 · Abstract (English)
LLM-based query expansion improves retrieval by enriching the original query with additional context. Yet most methods remain generation-driven, producing plausible pseudo-documents or expansions without checking how the target corpus responds. This can introduce retrieval drift, amplify misleading vocabulary, or miss terms that distinguish relevant from non-relevant documents. We argue that effective expansion requires retrieval-grounded feedback, not just single-pass generation or unverified iteration. We introduce ADORE (ADapt, Observe, Relevance Evaluate), an iterative framework that turns retrieval outcomes into feedback for the next expansion. At each round, an LLM generates pseudo-passages, a retriever exposes the corpus response, and a relevance assessor evaluates retrieved documents against the original query. These judgments identify what to reinforce, what remains undercovered, and what to suppress. Across TREC Deep Learning, BEIR, and BRIGHT, ADORE consistently outperforms strong query expansion baselines with notable improvements across nearly all evaluation settings, improving average nDCG@10 by 24.5% over BM25 and 3.6% over the strongest prior query expansion method on BEIR, and by 122.9% over BM25 and 9.2% over the best query expansion baseline on BRIGHT. Our code and data are publicly available.
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。