不增不漏：从预选文本片段中有效生成内容保留文本
Dont Add, dont Miss: Effective Content Preserving Generation from Pre-Selected Text Spans
AI总结：
本文针对受控文本缩减任务中内容保留约束执行不足和训练数据质量差的问题，提出结合强化学习训练、受控解码及GPT-4蒸馏的高质量开源CTR模型，ROUGE-L最高提升30分。
摘要：
最近提出的受控文本缩减（Controlled Text Reduction, CTR）任务将典型摘要式任务中的文本生成步骤独立出来。它要求模型生成连贯文本，并符合输入文本中预选的内容（“高亮片段”）。这种框架提升了摘要类任务的模块化程度，使得单一CTR模型能够与各种内容选择设置和模块相结合。然而，目前尚缺乏可靠的CTR模型，现有基线在该任务上的表现平平，难以满足实际应用需求。为此，我们引入了一个高质量的开源CTR模型，解决了此前两个关键局限：内容保留约束执行不足，以及银标训练数据质量欠佳。针对这些问题，我们在训练阶段通过强化学习（RL）强化内容保留约束，在推理阶段采用受控解码策略。此外，我们通过GPT-4蒸馏大幅提升了银标训练数据的质量。总体而言，将蒸馏数据集与高亮片段遵循策略相结合，相较于当前基线取得了显著提升，ROUGE-L分数最高提升30分，为下游应用提供了可靠的CTR模型。
英文摘要：
The recently introduced Controlled Text Reduction (CTR) task isolates the text generation step within typical summarization-style tasks. It does so by challenging models to generate coherent text conforming to pre-selected content within the input text (``highlights''). This framing enables increased modularity in summarization-like tasks, allowing to couple a single CTR model with various content-selection setups and modules. However, there are currently no reliable CTR models, while the performance of the existing baseline for the task is mediocre, falling short of practical utility. Here, we address this gap by introducing a high-quality, open-source CTR model that tackles two prior key limitations: inadequate enforcement of the content-preservation constraint, and suboptimal silver training data. Addressing these, we amplify the content-preservation constraint in both training, via RL, and inference, via a controlled decoding strategy. Further, we substantially improve the silver training data quality via GPT-4 distillation. Overall, pairing the distilled dataset with the highlight-adherence strategies yields marked gains over the current baseline, of up to 30 ROUGE-L points, providing a reliable CTR model for downstream use.
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。
