面向RAG的查询分解：平衡探索与利用
Query Decomposition for RAG: Balancing Exploration-Exploitation
AI总结：
该研究将RAG的查询分解与文档检索建模为探索-利用问题，用老虎机学习动态选子查询，结合排名和人工判断估相关性，提升了检索精度与长文本生成性能。
摘要：
检索增强生成（RAG）系统通过将复杂用户请求分解为子查询，为每个子查询检索潜在相关文档，再聚合这些文档生成答案，以此处理复杂用户请求。高效筛选有价值的文档需要平衡一项关键权衡：一是检索范围足够广以覆盖所有相关材料，二是限制检索范围以避免过多噪声和计算成本。我们将查询分解与文档检索问题建模为探索-利用场景，每次检索一份文档，以此建立对给定子查询效用的信念，并指导决策是继续利用当前子查询还是探索其他子查询。我们测试了多种老虎机学习方法，验证了它们在动态选择最具信息量子查询方面的有效性。我们的主要发现是：利用排名信息和人工判断估计文档相关性，可使文档级精度提升35%，α-nDCG提升15%，并在长文本生成下游任务上取得更优表现。
英文摘要：
Retrieval-augmented generation (RAG) systems address complex user requests by decomposing them into subqueries, retrieving potentially relevant documents for each, and then aggregating them to generate an answer. Efficiently selecting informative documents requires balancing a key trade-off: (i) retrieving broadly enough to capture all the relevant material, and (ii) limiting retrieval to avoid excessive noise and computational cost. We formulate query decomposition and document retrieval in an exploitation-exploration setting, where retrieving one document at a time builds a belief about the utility of a given sub-query and informs the decision to continue exploiting or exploring an alternative. We experiment with a variety of bandit learning methods and demonstrate their effectiveness in dynamically selecting the most informative sub-queries. Our main finding is that estimating document relevance using rank information and human judgments yields a 35% gain in document-level precision, 15% increase in α-nDCG, and better performance on the downstream task of long-form generation.
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。
