用经典反馈模型提升LLM查询扩展效果，让搜索更准
Revisiting Feedback Models for HyDE
- 用Rocchio等传统反馈模型优化LLM生成的查询扩展
- 在BM25检索器上，准确率显著高于简单拼接方法
- 适合想改进大模型搜索效果的研究者和工程师
近期利用大语言模型（LLM）进行伪相关反馈（PRF）的方法，通常未采用如Rocchio和RM3等成熟的反馈模型来扩展查询，而是简单拼接查询与LLM生成的扩展内容。但这种方法是否最优？我们重新审视并系统评估了传统反馈模型在HyDE（一种通过LLM生成假设答案文档来丰富查询表示的方法）中的应用。实验表明，使用Rocchio等反馈算法提取并加权扩展词，可显著提升HyDE的效果，为基于LLM的伪相关反馈方法提供了一种简单有效的精度增强方式。
原文摘要 · Abstract (English)
Recent approaches that leverage large language models (LLMs) for pseudo-relevance feedback (PRF) have generally not utilized well-established feedback models like Rocchio and RM3 when expanding queries for sparse retrievers like BM25. Instead, they often opt for a simple string concatenation of the query and LLM-generated expansion content. But is this optimal? To answer this question, we revisit and systematically evaluate traditional feedback models in the context of HyDE, a popular method that enriches query representations with LLM-generated hypothetical answer documents. Our experiments show that HyDE's effectiveness can be substantially improved when leveraging feedback algorithms such as Rocchio to extract and weight expansion terms, providing a simple way to further enhance the accuracy of LLM-based PRF methods.
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。