Recently, large language models (LLMs) have demonstrated remarkable performance in abstractive summarization tasks. However, controllable summarization with LLMs remains underexplored, limiting their ability to generate summaries that align with specific user preferences. In this paper, we first investigate the capability of LLMs to control diverse attributes, revealing that they encounter greater challenges with numerical attributes, such as length and extractiveness, compared to linguistic attributes. To address this challenge, we propose a guide-to-explain framework (GTE) for controllable summarization. Our GTE framework enables the model to identify misaligned attributes in the initial draft and guides it in explaining errors in the previous output. Based on this reflection, the model generates a well-adjusted summary. As a result, by allowing the model to reflect on its misalignment, we generate summaries that satisfy the desired attributes in surprisingly fewer iterations than other iterative methods solely using LLMs.

翻译：近年来，大型语言模型（LLMs）在抽象摘要任务中展现出卓越性能。然而，基于LLMs的可控摘要研究仍显不足，限制了其生成符合特定用户偏好摘要的能力。本文首先探究了LLMs控制多样化属性的能力，发现相较于语言属性，LLMs在处理数值属性（如长度和抽取程度）时面临更大挑战。为应对这一挑战，我们提出了一种用于可控摘要的引导解释框架（GTE）。该框架使模型能够识别初始草稿中未对齐的属性，并引导其解释先前输出中的错误。基于此反思，模型生成经过优化调整的摘要。结果表明，通过让模型反思其未对齐问题，我们能够以远少于其他仅使用LLMs的迭代方法的迭代次数，生成满足目标属性的摘要。