PlanRAG：面向作为决策者的生成式大语言模型的先规划后检索增强生成方法
PlanRAG: A Plan-then-Retrieval Augmented Generation for Generative Large Language Models as Decision Makers
AI总结：
针对需要复杂数据分析的决策制定任务，该研究定义了决策问答任务，构建了DQA基准，并提出迭代式先规划后检索增强生成方法PlanRAG，在两类场景下性能均优于现有最优迭代RAG方法。
摘要：
本文开展了一项将大语言模型（LLMs）用于需要复杂数据分析的决策制定解决方案的研究。我们将决策问答（Decision QA）定义为针对决策问题$Q$、业务规则$R$和数据库$D$给出最优决策$d_{best}$的任务。由于目前没有可检验决策问答任务的基准，我们提出了决策问答基准DQA，它包含定位（Locating）和建造（Building）两种场景，由两款与决策问答目标几乎一致的电子游戏（《欧陆风云4》和《维多利亚3》）构建而来。为有效解决决策问答问题，我们还提出了一种名为迭代式先规划后检索增强生成（PlanRAG）的新型RAG技术。我们基于PlanRAG的语言模型第一步生成决策规划，第二步由检索器生成数据分析查询。该方法在定位场景下比当前最优的迭代RAG方法性能高15.8%，在建造场景下高7.4%。我们已在https://github.com/myeon9h/PlanRAG发布代码和基准。
英文摘要：
In this paper, we conduct a study to utilize LLMs as a solution for decision making that requires complex data analysis. We define Decision QA as the task of answering the best decision, $d_{best}$, for a decision-making question $Q$, business rules $R$ and a database $D$. Since there is no benchmark that can examine Decision QA, we propose Decision QA benchmark, DQA. It has two scenarios, Locating and Building, constructed from two video games (Europa Universalis IV and Victoria 3) that have almost the same goal as Decision QA. To address Decision QA effectively, we also propose a new RAG technique called the iterative plan-then-retrieval augmented generation (PlanRAG). Our PlanRAG-based LM generates the plan for decision making as the first step, and the retriever generates the queries for data analysis as the second step. The proposed method outperforms the state-of-the-art iterative RAG method by 15.8% in the Locating scenario and by 7.4% in the Building scenario, respectively. We release our code and benchmark at https://github.com/myeon9h/PlanRAG.
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。
