用可复用的改写模式让大模型更精准地优化搜索词。
ReFormeR: Learning and Applying Explicit Query Reformulation Patterns
- 先从查询对中提取短改写模式，构建可迁移的模式库。
- 在TREC DL 2019/2020/Hard上优于经典与主流LMM改写方法。
- 适合需要可控、可解释改写的搜索系统研发者。
我们提出ReFormeR，一种基于模式引导的查询改写方法。不同于直接让大语言模型生成改写结果，ReFormeR首先从初始查询与更强改写结果的配对中提取短改写模式，将其整合为一个紧凑的可迁移模式库，并根据新查询的检索上下文选择合适的改写模式。所选模式约束改写操作于特定类型，如语义消歧、词汇锚定或判别性特征添加等。该方法使改写策略显式化，引导大模型实现目标明确且高效的查询改写。在TREC DL 2019、DL 2020和DL Hard上的大量实验表明，其性能持续优于经典反馈方法及近期基于LLM的查询改写与扩展方法。
原文摘要 · Abstract (English)
We present ReFormeR, a pattern-guided approach for query reformulation. Instead of prompting a language model to generate reformulations of a query directly, ReFormeR first elicits short reformulation patterns from pairs of initial queries and empirically stronger reformulations, consolidates them into a compact library of transferable reformulation patterns, and then selects an appropriate reformulation pattern for a new query given its retrieval context. The selected pattern constrains query reformulation to controlled operations such as sense disambiguation, vocabulary grounding, or discriminative facet addition, to name a few. As such, our proposed approach makes the reformulation policy explicit through these reformulation patterns, guiding the LLM towards targeted and effective query reformulations. Our extensive experiments on TREC DL 2019, DL 2020, and DL Hard show consistent improvements over classical feedback methods and recent LLM-based query reformulation and expansion approaches.
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。