大模型通过反馈训练成数字诗人，人类难辨真伪。
Creating a digital poet
- 用迭代提示反馈塑造模型风格，不重新训练。
- 盲测中人类识别AI诗准确率仅54%，与随机无异。
- 成果被出版社出版，引发对创作与作者身份的讨论。
机器能写出好诗吗？若能，将引发关于艺术本质与价值的根本性问题。我们开展了一场为期七个月的诗歌工作坊，通过迭代式上下文专家反馈，将大型语言模型塑造成数字诗人，无需重训练。在多个阶段中，模型发展出独特风格和连贯作品集，经定量与定性分析验证，并生成笔名与作者图像。在一项盲测中，50名人文领域学生及毕业生（每组含3首AI诗和3首知名诗人作品）的判断结果接近随机：人类诗被识别为人类的占比为54%，AI诗被识别为AI的占比为52%，95%置信区间包含50%。工作坊结束后，一家商业出版社发行了该模型创作的诗集。结果表明，工作坊式提示可支持长期创造性塑造，并重启关于创造力与作者身份的讨论。
原文摘要 · Abstract (English)
Can a machine write good poetry? Any positive answer raises fundamental questions about the nature and value of art. We report a seven-month poetry workshop in which a large language model was shaped into a digital poet through iterative in-context expert feedback, without retraining. Across sessions, the model developed a distinctive style and a coherent corpus, supported by quantitative and qualitative analyses, and it produced a pen name and author image. In a blinded authorship test with 50 humanities students and graduates (three AI poems and three poems by well-known poets each), judgments were at chance: human poems were labeled human 54% of the time and AI poems 52%, with 95% confidence intervals including 50%. After the workshop, a commercial publisher released a poetry collection authored by the model. These results show that workshop-style prompting can support long-horizon creative shaping and renew debates on creativity and authorship.
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。