探索基于大语言模型的可控制摘要方法
Exploring Iterative Controllable Summarization with Large Language Models
AI总结：
本文提出GTE框架，通过迭代优化提升大语言模型在可控摘要任务中的性能，有效解决属性控制难题。
摘要：
大语言模型（LLMs）在抽象摘要任务中展示了卓越的性能。然而，它们对摘要属性（如长度或主题）的精确控制能力仍处于探索阶段，限制了其适应特定用户需求的能力。在本文中，我们系统地探讨了LLMs的可控性。为此，我们重新审视摘要属性测量，并引入迭代评估指标，失败率和平均迭代次数，以精确评估LLMs的可控性，而不仅仅是评估错误。我们的发现表明，LLMs在处理数值属性时比处理语言属性更具挑战性。为了解决这一挑战，我们提出了一种指导-解释框架（GTE）用于可控摘要。我们的GTE框架使模型能够识别初始草稿中的不匹配属性，并指导其在先前输出中自我解释错误。通过允许模型反思其不匹配，GTE生成了满足所需属性的高质量摘要，具有稳健的有效性，所需的迭代次数比其他迭代方法少得多。
英文摘要：
Large language models (LLMs) have demonstrated remarkable performance in abstractive summarization tasks. However, their ability to precisely control summary attributes (e.g., length or topic) remains underexplored, limiting their adaptability to specific user preferences. In this paper, we systematically explore the controllability of LLMs. To this end, we revisit summary attribute measurements and introduce iterative evaluation metrics, failure rate and average iteration count to precisely evaluate controllability of LLMs, rather than merely assessing errors. Our findings show that LLMs struggle more with numerical attributes than with 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 self-explaining errors in the previous output. By allowing the model to reflect on its misalignment, GTE generates well-adjusted summaries that satisfy the desired attributes with robust effectiveness, requiring surprisingly fewer iterations than other iterative approaches.
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。
