用相似主题范文生成新主题说明文，更准更连贯。
Writing Like the Best: Exemplar-Based Expository Text Generation
- 分段模仿+动态调整，让模型学得更精准
- 在3个数据集上表现优于现有方法，内容更真实一致
- 适合想快速写高质量说明文的研究者或创作者
我们提出「范例式说明文生成」任务，旨在利用相似主题的范例，生成关于新主题的说明性文本。当前方法因依赖大量范例数据、难以适配特定主题内容，且长文本连贯性差而受限。为此，我们提出「自适应模仿」概念，并设计新的递归式「计划-再适应」（RePA）框架。RePA通过细粒度的计划-再适应流程，利用大语言模型实现高效自适应模仿，并支持逐段递归模仿，结合两种记忆结构提升输入清晰度与输出连贯性。我们还构建了基于大语言模型的专用评估指标——模仿度、适应度与适应性模仿度。在三个多样数据集上的实验表明，RePA在生成事实准确、内容一致且相关性强的文本方面显著优于现有基线。
原文摘要 · Abstract (English)
We introduce the Exemplar-Based Expository Text Generation task, aiming to generate an expository text on a new topic using an exemplar on a similar topic. Current methods fall short due to their reliance on extensive exemplar data, difficulty in adapting topic-specific content, and issues with long-text coherence. To address these challenges, we propose the concept of Adaptive Imitation and present a novel Recurrent Plan-then-Adapt (RePA) framework. RePA leverages large language models (LLMs) for effective adaptive imitation through a fine-grained plan-then-adapt process. RePA also enables recurrent segment-by-segment imitation, supported by two memory structures that enhance input clarity and output coherence. We also develop task-specific evaluation metrics--imitativeness, adaptiveness, and adaptive-imitativeness--using LLMs as evaluators. Experimental results across our collected three diverse datasets demonstrate that RePA surpasses existing baselines in producing factual, consistent, and relevant texts for this task.
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。