用逆向提示框架让大模型零样本生成高质量古诗。
BIPro: Zero-shot Chinese Poem Generation via Block Inverse Prompting Constrained Generation Framework
- 提出块逆提示框架，模拟人类写诗分步构思过程。
- 仅用中文版GLM-10B，零样本生成效果超越GPT-4等主流模型。
- 适合对古诗生成质量要求高、追求零训练成本的研究者。
生成式预训练模型虽在跨领域任务中表现突出，但在开放标题下的传统形式中文诗歌生成等受限写作任务中仍面临挑战。为此，我们提出块逆提示（BIPro）约束生成框架，采用‘修正’与‘重写’两种逆向提示方法，模拟人类分步创作文本的过程，显著提升零样本条件下开放域传统形式中文诗歌生成的质量。基于较弱的块生成模型GLM-10B-Chinese，BIPro在不使用提示词或额外训练的情况下，生成的诗歌在专业诗人的人工评估中，优于GPT-4、GLM-4等先进直接生成系统，以及语生、十三百、百度诗歌助手等专用系统。此外，人工评估还显示，该方法大幅缩小了人工智能作品与入围人类文学作品之间的差距，揭示了块生成模型在受限生成任务中的巨大潜力。
原文摘要 · Abstract (English)
Recently, generative pre-trained models have made significant strides, particularly highlighted by the release of ChatGPT and GPT-4, which exhibit superior cross-domain capabilities. However, these models still face challenges on constrained writing tasks like poem generation under open-domain titles. In response to this challenge, we introduce Block Inverse Prompting (BIPro) constrained generation framework. BIPro leverages two block inverse prompting methods, revise and rewrite, that mimic the process of human text writing using block generative models. It significantly improves the zero-shot generation quality on the formidable constrained generation task of open-domain traditional-form Chinese poem generation. Based on a less powerful block generative model GLM-10B-Chinese, poems composed via BIPro without priming or additional training outperform both most advanced direct generative systems like GPT-4 or GLM-4 and best domain-specific systems such as Yusheng, Shisanbai, or Baidu Poetry Helper in human evaluation by proficient poets. Finally, BIPro considerably narrows the gap between AI-generated works and short-listed human literary arts in another human evaluation, unveiling the promising potential of block generative models in improving the quality of constrained generation.
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。