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：随着大型语言模型在信息检索场景中部署需求的日益增长，开发可验证系统的工作正持续推进，这类系统能够针对查询生成附带支持证据的响应。本文探讨了基于规划的模型的归因能力，近期研究表明此类模型能够提升生成文本的忠实性、事实依据性与可控性。我们将规划概念化为一系列问题构成的序列，这些问题作为生成内容及其组织结构的蓝图。我们提出了两种利用不同蓝图变体的归因模型：一种抽象模型通过全新生成问题构建蓝图，另一种抽取模型则通过复制输入内容中的问题形成蓝图。在长文本问答任务上的实验表明，规划策略能持续提升归因质量。此外，相较于缺乏规划组件的基于大型语言模型的流程，蓝图模型生成的引用标注具有更高的准确性。