通过迭代效用最大化学习为多个检索增强模型排序
Learning to Rank for Multiple Retrieval-Augmented Models through Iterative Utility Maximization
AI总结：
本文提出一种迭代效用最大化方法，通过离线反馈与期望最大化算法优化统一搜索引擎，并支持在线实时调整，有效为多个RAG智能体实现个性化检索，在KILT基准的18个模型上显著优于基线。
摘要：
本文研究了统一搜索引擎的设计，旨在服务于多个检索增强生成（RAG）智能体，每个智能体具有不同的任务、骨干大语言模型（LLM）和RAG策略。我们引入了一种迭代方法，在离线阶段，搜索引擎为RAG智能体生成检索结果，并收集关于检索文档质量的反馈。随后，利用期望最大化算法，使用这些反馈迭代优化搜索引擎，目标是最大化每个智能体的效用函数。此外，我们将该方法适配到在线场景，使搜索引擎能根据实时的单个智能体反馈来优化其行为，从而更好地为每个智能体提供结果。在知识密集型语言任务（KILT）基准的数据集上的实验表明，我们的方法在18个RAG模型上平均显著优于基线。我们证明了该方法能基于收集的反馈有效为每个RAG智能体“个性化”检索。最后，我们提供了全面的消融研究以探讨方法的各个方面。
英文摘要：
This paper investigates the design of a unified search engine to serve multiple retrieval-augmented generation (RAG) agents, each with a distinct task, backbone large language model (LLM), and RAG strategy. We introduce an iterative approach where the search engine generates retrieval results for the RAG agents and gathers feedback on the quality of the retrieved documents during an offline phase. This feedback is then used to iteratively optimize the search engine using an expectation-maximization algorithm, with the goal of maximizing each agent's utility function. Additionally, we adapt this to an online setting, allowing the search engine to refine its behavior based on real-time individual agents feedback to better serve the results for each of them. Experiments on datasets from the Knowledge-Intensive Language Tasks (KILT) benchmark demonstrates that our approach significantly on average outperforms baselines across 18 RAG models. We demonstrate that our method effectively ``personalizes'' the retrieval for each RAG agent based on the collected feedback. Finally, we provide a comprehensive ablation study to explore various aspects of our method.
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。
