LLM生成内容看似优秀实则空洞，本质是系统性产出媚俗作品。
LLMs Generate Kitsch
- 通过训练机制分析，指出LLM生成内容具有媚俗（kitsch）倾向
- 控制定义后，读者普遍认为LLM故事更媚俗
- 为评估生成内容质量提供新视角，适合关注创意本质的研究者
大型语言模型（LLMs）正被广泛用于生成图片、文字、音乐、视频等传统上需人类创造力的作品。在受控研究中，LLM生成的作品常被评为优于人类创作。然而，这些作品也常显得平庸且缺乏深度。本文提出，这种矛盾源于LLM系统性地生成媚俗（kitsch）内容，而这正是其训练方式的必然结果。我们通过实证发现，在控制‘媚俗’定义的前提下，读者确实感知到LLM生成的故事更具媚俗特征。该研究对未来的评估方法及创造性任务（如科研与编程）设计具有重要启示。
原文摘要 · Abstract (English)
Large Language Models (LLMs) are increasingly used to generate pictures, texts, music, videos, and other works that have traditionally required human creativity. LLM-generated artifacts are often rated better than human-generated works in controlled studies. At the same time, they can come across as generic and hollow. We propose to resolve this tension by arguing that LLMs systematically generate kitsch, and that this is a consequence of the way in which they are trained. We also show empirically that readers perceive LLM-generated stories as kitschier, if we control for their definition of "kitsch". We discuss implications for the design of future studies and for creative tasks such as research and coding.
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。