通过评分排序损失，实现对摘要质量维度的精准控制
Learning to Control Summaries with Score Ranking
- 用模型评估得分设计损失函数，实现细粒度控制
- 在保持高质量的同时，可灵活优先某项指标
- 适用于需要定制化摘要输出的研究与应用
近期摘要研究致力于在完整性、简洁性和忠实性等多个维度上协同提升摘要质量。然而，这些工作大多忽视了在各维度存在固有权衡时，如何对生成过程进行个体化控制的问题。例如，提高简洁性可能损害完整性。本文提出一种损失函数，使模型输出与细粒度的模型评估得分（如 FineSurE）对齐，从而在提升整体质量的同时，支持对特定质量维度的可控调节。在 LLaMA、Qwen 和 Mistral 三个预训练模型上的实验表明，该方法性能达到当前顶尖水平，且首次实现了对单一质量维度的强可控性。
原文摘要 · Abstract (English)
Recent advances in summarization research focus on improving summary quality across multiple criteria, such as completeness, conciseness, and faithfulness, by jointly optimizing these dimensions. However, these efforts largely overlook the challenge of controlling summary generation with respect to individual criteria, especially in the presence of their inherent trade-offs. For example, enhancing conciseness can compromise completeness, and vice versa. In this work, we address this gap by proposing a loss function that aligns model outputs with fine-grained, model-based evaluation scores (e.g., from FineSurE), enabling both improvement in summary quality and dimension-specific control. Our approach improves the overall quality of summaries while maintaining the ability to selectively prioritize one criterion over others. Experiments on three pretrained models (LLaMA, Qwen, and Mistral) demonstrate that our method achieves performance comparable to state-of-the-art summarizers, while uniquely offering strong controllability over individual quality dimensions.
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。