通过分步规划与优化，提升大模型生成答案的多样性和全面性。
Plan-and-Refine: Diverse and Comprehensive Retrieval-Augmented Generation
- 先生成多个不同角度的提问计划，再逐个细化回答。
- 在ANTIQUE和TREC数据集上分别提升13.1%和15.41%。
- 适合需要全面、多视角信息的任务场景。
本文研究大语言模型在生成多样化和全面性回答时的局限性，提出基于两阶段设计的Plan-and-Refine（P&R）框架。第一阶段为全局探索，生成针对输入问题的多样化计划，每个计划包含多个不同查询维度及其附加描述；第二阶段为局部优化，基于每项计划生成并迭代优化回答提案，最终通过奖励模型筛选事实准确且覆盖全面的最优方案。实验采用ICAT评估方法，在来自非事实型问答和TREC搜索结果多样化任务的两个多样化信息检索基准上验证效果。结果显示，P&R显著优于基线模型，在ANTIQUE数据集上提升13.1%，在TREC数据集上提升15.41%。小型用户研究进一步证实该框架的有效性。
原文摘要 · Abstract (English)
This paper studies the limitations of (retrieval-augmented) large language models (LLMs) in generating diverse and comprehensive responses, and introduces the Plan-and-Refine (P&R) framework based on a two phase system design. In the global exploration phase, P&R generates a diverse set of plans for the given input, where each plan consists of a list of diverse query aspects with corresponding additional descriptions. This phase is followed by a local exploitation phase that generates a response proposal for the input query conditioned on each plan and iteratively refines the proposal for improving the proposal quality. Finally, a reward model is employed to select the proposal with the highest factuality and coverage. We conduct our experiments based on the ICAT evaluation methodology--a recent approach for answer factuality and comprehensiveness evaluation. Experiments on the two diverse information seeking benchmarks adopted from non-factoid question answering and TREC search result diversification tasks demonstrate that P&R significantly outperforms baselines, achieving up to a 13.1% improvement on the ANTIQUE dataset and a 15.41% improvement on the TREC dataset. Furthermore, a smaller scale user study confirms the substantial efficacy of the P&R framework.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。