arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2406.14979cs.CL
收藏

Retrieve-Plan-Generation:面向知识密集型大语言模型生成的迭代规划与回答框架

Retrieve-Plan-Generation: An Iterative Planning and Answering Framework for Knowledge-Intensive LLM Generation

University of Science and Technology of China(中国科学技术大学);Anhui Conch Information Technology Engineering Co., Ltd.(安徽海螺信息技术工程有限责任公司)

Yuanjie Lyu, Zihan Niu, Zheyong Xie, Chao Zhang, Tong Xu, Yang Wang, Enhong Chen

AI总结:

针对大语言模型知识不足易出错、现有RAG方法易受无关检索内容干扰的问题,提出迭代式检索-规划-生成RPG框架,通过多任务提示调优让模型交替规划与基于相关细粒度段落生成,在5项知识密集型任务上验证了有效性。

摘要:

尽管大语言模型(LLMs)在各类任务中已取得显著进展,但受限于内部知识储备,它们常会产生事实性错误。检索增强生成(RAG)通过外部知识源增强LLMs的能力,是一种颇具前景的解决方案。但这类方法可能被检索文档中的无关段落误导。由于LLM生成存在固有不确定性,输入完整文档可能引入偏离主题的信息,导致模型偏离核心议题,影响生成内容的相关性。为解决这些问题,我们提出Retrieve-Plan-Generation(RPG,检索-规划-生成)框架。RPG在规划阶段生成规划令牌,用于引导后续生成过程;在回答阶段,模型根据规划选择相关的细粒度段落,用于后续答案生成。该规划-回答过程会迭代重复直至完成,通过聚焦特定主题提升生成内容的相关性。为高效实现该框架,我们采用了一种简单但有效的多任务提示调优方法,使现有LLMs能够同时处理规划和回答任务。我们在5项知识密集型生成任务上将RPG与各基线模型进行了全面对比,验证了所提方法的有效性。

英文摘要:

Despite the significant progress of large language models (LLMs) in various tasks, they often produce factual errors due to their limited internal knowledge. Retrieval-Augmented Generation (RAG), which enhances LLMs with external knowledge sources, offers a promising solution. However, these methods can be misled by irrelevant paragraphs in retrieved documents. Due to the inherent uncertainty in LLM generation, inputting the entire document may introduce off-topic information, causing the model to deviate from the central topic and affecting the relevance of the generated content. To address these issues, we propose the Retrieve-Plan-Generation (RPG) framework. RPG generates plan tokens to guide subsequent generation in the plan stage. In the answer stage, the model selects relevant fine-grained paragraphs based on the plan and uses them for further answer generation. This plan-answer process is repeated iteratively until completion, enhancing generation relevance by focusing on specific topics. To implement this framework efficiently, we utilize a simple but effective multi-task prompt-tuning method, enabling the existing LLMs to handle both planning and answering. We comprehensively compare RPG with baselines across 5 knowledge-intensive generation tasks, demonstrating the effectiveness of our approach.

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。

↑