用小模型生成文档并过滤幻觉内容，提升搜索查询扩展效果。
GOLFer: Smaller LM-Generated Documents Hallucination Filter & Combiner for Query Expansion in Information Retrieval
- 用小模型生成候选文档，通过过滤器剔除虚假内容。
- 结合过滤后内容与原查询，用加权方式提升检索效果。
- 在多个数据集上表现优于小模型方法，接近大模型水平。
基于大语言模型（LLM）的查询扩展通过生成假设性文档来增强查询，但其性能高度依赖模型规模，导致计算成本高、访问受限。为解决此问题，我们提出GOLFer——一种利用小型开源语言模型进行查询扩展的新方法。GOLFer包含两个模块：幻觉过滤器用于检测并移除生成文档中非事实性和不一致的语句（小模型常见问题），文档组合器则通过权重向量将过滤后的文本与原始查询融合，平衡两者影响。我们在三个网页搜索数据集和十个低资源数据集上评估GOLFer，结果表明，相较于使用小模型的方法，GOLFer始终表现更优；同时，在多数场景下其性能可媲美使用大型语言模型的方法，证明了该方法的有效性。
原文摘要 · Abstract (English)
Large language models (LLMs)-based query expansion for information retrieval augments queries with generated hypothetical documents with LLMs. However, its performance relies heavily on the scale of the language models (LMs), necessitating larger, more advanced LLMs. This approach is costly, computationally intensive, and often has limited accessibility. To address these limitations, we introduce GOLFer - Smaller LMs-Generated Documents Hallucination Filter & Combiner - a novel method leveraging smaller open-source LMs for query expansion. GOLFer comprises two modules: a hallucination filter and a documents combiner. The former detects and removes non-factual and inconsistent sentences in generated documents, a common issue with smaller LMs, while the latter combines the filtered content with the query using a weight vector to balance their influence. We evaluate GOLFer alongside dominant LLM-based query expansion methods on three web search and ten low-resource datasets. Experimental results demonstrate that GOLFer consistently outperforms other methods using smaller LMs, and maintains competitive performance against methods using large-size LLMs, demonstrating its effectiveness.
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。