The increasing demand for the deployment of LLMs in information-seeking scenarios has spurred efforts in creating verifiable systems, which generate responses to queries along with supporting evidence. In this paper, we explore the attribution capabilities of plan-based models which have been recently shown to improve the faithfulness, grounding, and controllability of generated text. We conceptualize plans as a sequence of questions which serve as blueprints of the generated content and its organization. We propose two attribution models that utilize different variants of blueprints, an abstractive model where questions are generated from scratch, and an extractive model where questions are copied from the input. Experiments on long-form question-answering show that planning consistently improves attribution quality. Moreover, the citations generated by blueprint models are more accurate compared to those obtained from LLM-based pipelines lacking a planning component.

翻译：随着大语言模型（LLM）在信息检索场景中的部署需求日益增长，构建可验证系统（即能生成查询响应并附带支持证据的系统）成为研究热点。本文探索了基于规划模型的可归因能力——近期研究表明这类模型能提升生成文本的忠实性、可溯源性及可控性。我们将规划概念化为一系列问题构成的蓝图，这些问题决定了生成内容及其组织结构。我们提出两种利用不同蓝图变体的归因模型：一种是抽象模型，从头开始生成问题；另一种是抽取模型，从输入中复制问题。在长篇问答任务上的实验表明，规划能持续提升归因质量。此外，蓝图模型生成的引文相较于缺乏规划模块的基于LLM的流水线系统生成的引文具有更高的准确性。