我们能一次性检索所有内容吗？ARM：一种基于对齐导向的 LLM 检索方法
Can we Retrieve Everything All at Once? ARM: An Alignment-Oriented LLM-based Retrieval Method
AI总结：
针对复杂问题检索效率低的问题，提出基于LLM的ARM方法，通过探索数据对象关系实现问题与数据组织的对齐，在Bird和OTT-QA数据集上准确率显著优于标准RAG和agentic RAG。
摘要：
现实世界的开放域问题可能很复杂，特别是当回答它们涉及来自多个信息源的信息时。LLMs 在将复杂任务分解为更简单的步骤方面表现出了令人印象深刻的性能，之前的工作利用它进行更好的检索以支持复杂问题。然而，LLMs 对问题的分解并不了解有哪些可用数据以及数据是如何组织的，这通常导致次优的检索性能。最近在 agentic RAG 方面的努力提出以迭代方式执行检索，其中后续查询是作为基于先前检索轮次的动作得出的。虽然这提供了一种与数据集合交互的方式，但 agentic RAG 对数据的探索效率低下，因为连续的查询依赖于先前的结果，而不是受集合中可用数据组织的指导。为了解决这个问题，我们提出了一种基于 LLM 的检索方法——ARM，旨在通过探索数据对象之间的关系（而不仅仅是匹配查询的表述）来更好地将问题与数据集合的组织对齐，从而为复杂查询提供一种一次性检索全部的解决方案。我们在两个数据集 Bird 和 OTT-QA 上评估了 ARM。在 Bird 上，它在执行准确率上比带有查询分解的标准 RAG 高出多达 5.2 个百分点，比 agentic RAG (ReAct) 高出多达 15.9 个百分点。在 OTT-QA 上，与这些方法相比，它实现了高出多达 5.5 个百分点和 19.3 个百分点的 F1 匹配分数。
英文摘要：
Real-world open-domain questions can be complicated, particularly when answering them involves information from multiple information sources. LLMs have demonstrated impressive performance in decomposing complex tasks into simpler steps, and previous work has used it for better retrieval in support of complex questions. However, LLM's decomposition of questions is unaware of what data is available and how data is organized, often leading to a sub-optimal retrieval performance. Recent effort in agentic RAG proposes to perform retrieval in an iterative fashion, where a followup query is derived as an action based on previous rounds of retrieval. While this provides one way of interacting with the data collection, agentic RAG's exploration of data is inefficient because successive queries depend on previous results rather than being guided by the organization of available data in the collection. To address this problem, we propose an LLM-based retrieval method -- ARM, that aims to better align the question with the organization of the data collection by exploring relationships among data objects beyond matching the utterance of the query, thus leading to a retrieve-all-at-once solution for complex queries. We evaluated ARM on two datasets, Bird and OTT-QA. On Bird, it outperforms standard RAG with query decomposition by up to 5.2 pt in execution accuracy and agentic RAG (ReAct) by up to 15.9 pt. On OTT-QA, it achieves up to 5.5 pt and 19.3 pt higher F1 match scores compared to these approaches.
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。
