让大模型通过自我纠错生成精准控制的摘要，少迭代就能达标。
Exploring Iterative Controllable Summarization with Large Language Models
- 用自解释错误反馈机制引导模型逐步修正摘要偏差
- 数值类属性控制失败率高，语言类属性更稳定
- 只需少量迭代即可达成目标，适合需要精准摘要的场景
大语言模型在抽象摘要任务中表现优异，但对摘要长度、主题等属性的精确控制仍不充分，限制了其满足用户特定需求的能力。本文系统探索大模型的可控性，重新审视摘要属性评估方法，提出迭代评估指标：失败率与平均迭代次数，以更精准衡量可控性，而非仅关注错误。研究发现，大模型在数值类属性控制上表现更差。为此，我们提出指导-解释框架（GTE），使模型能识别初稿中属性偏差，并通过自我解释先前输出中的错误进行修正。该机制让模型能够反思并调整自身输出，生成符合目标属性的摘要，且效果稳健，所需迭代次数远少于其他迭代方法。
原文摘要 · Abstract (English)
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.
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。