用大模型迭代优化广告文案，让内容更符合多重要求且点击率更高。
LLM-driven Constrained Copy Generation through Iterative Refinement
- 基于大模型的迭代优化框架，逐步修正文案以满足长度、关键词、语气等多重约束。
- 在电商横幅文案任务中，成功率提升16.25%至35.91%，点击率提高38.5%至45.21%。
- 适合需要高个性化、多约束生成的营销自动化场景，尤其对广告文案优化有直接价值。
撰写广告文案（copywriting）是一项具有挑战性的生成任务，因需满足多种约束条件。人类创作过程本质上是迭代的：从初稿开始，经过多次修改。然而，人工创作耗时费力，导致每个场景仅能产出少量文案，限制了内容个性化。尽管大语言模型（LLM）可快速生成文案，但首次生成往往无法完全满足所有约束（类似人类）。现有研究虽在简单约束任务中展示出迭代优化潜力，但在涉及多个复杂约束的文案生成任务中仍缺乏验证。为此，本文提出一种基于大模型的端到端迭代优化框架，实现可扩展的文案生成。据我们所知，这是首个同时处理多个复杂约束的文案生成研究，包括长度、主题、关键词、词汇顺序偏好及语气风格。我们在三个不同复杂度的电商横幅文案任务中验证该框架，结果显示，迭代优化使文案成功率提升16.25%–35.91%。此外，在多项采用多臂老虎机框架的试点研究中，该方法生成的文案优于人工撰写的版本，最优文案点击率提升38.5%–45.21%。
原文摘要 · Abstract (English)
Crafting a marketing message (copy), or copywriting is a challenging generation task, as the copy must adhere to various constraints. Copy creation is inherently iterative for humans, starting with an initial draft followed by successive refinements. However, manual copy creation is time-consuming and expensive, resulting in only a few copies for each use case. This limitation restricts our ability to personalize content to customers. Contrary to the manual approach, LLMs can generate copies quickly, but the generated content does not consistently meet all the constraints on the first attempt (similar to humans). While recent studies have shown promise in improving constrained generation through iterative refinement, they have primarily addressed tasks with only a few simple constraints. Consequently, the effectiveness of iterative refinement for tasks such as copy generation, which involves many intricate constraints, remains unclear. To address this gap, we propose an LLM-based end-to-end framework for scalable copy generation using iterative refinement. To the best of our knowledge, this is the first study to address multiple challenging constraints simultaneously in copy generation. Examples of these constraints include length, topics, keywords, preferred lexical ordering, and tone of voice. We demonstrate the performance of our framework by creating copies for e-commerce banners for three different use cases of varying complexity. Our results show that iterative refinement increases the copy success rate by $16.25-35.91$% across use cases. Furthermore, the copies generated using our approach outperformed manually created content in multiple pilot studies using a multi-armed bandit framework. The winning copy improved the click-through rate by $38.5-45.21$%.
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。