让生成模型的错误变创意，通过五阶段流程提升创造力。
E.A.R.T.H.: Structuring Creative Evolution through Model Error in Generative AI
- 用错误生成与反馈循环，将模型失误转化为创意资产。
- 创意评分提升70.4%，标语更短更新颖，图文对齐度高。
- 适合想打造自进化创意AI的研究者与设计师使用。
如何让AI从模仿走向真正创造？本文提出E.A.R.T.H.框架，一个五阶段生成流程，通过错误生成、放大、精炼选择、转换和利用反馈，将模型生成错误转化为创意资产。基于认知科学与生成建模，提出‘创意蕴藏于失败’的假设，并通过结构化提示、语义评分和人机评估实现。采用LLaMA-2-7B-Chat、SBERT、BERTScore、CLIP、BLIP-2和Stable Diffusion，构建融合新颖性、惊喜度与相关性的复合奖励函数。在精炼阶段，创意评分从1.179升至1.898（t = -5.56, p < 0.001），最终输出达2.010，提升70.4%；优化标语长度减少48.4%，新颖性提高40.7%，相关性仅下降4.0%。跨模态测试显示强图文对齐（CLIPScore: 0.249；BERTScore F1: 0.816）。人工评估一致认可高质量创意与表达清晰度，反馈强调风格精准与情感共鸣。结果表明，以错误为中心、反馈驱动的生成机制能显著增强创造力，为可扩展的自演化人类对齐创意AI提供路径。
原文摘要 · Abstract (English)
How can AI move beyond imitation toward genuine creativity? This paper proposes the E.A.R.T.H. framework, a five-stage generative pipeline that transforms model-generated errors into creative assets through Error generation, Amplification, Refine selection, Transform, and Harness feedback. Drawing on cognitive science and generative modeling, we posit that "creative potential hides in failure" and operationalize this via structured prompts, semantic scoring, and human-in-the-loop evaluation. Implemented using LLaMA-2-7B-Chat, SBERT, BERTScore, CLIP, BLIP-2, and Stable Diffusion, the pipeline employs a composite reward function based on novelty, surprise, and relevance. At the Refine stage, creativity scores increase by 52.5% (1.179 to 1.898, t = -5.56, p < 0.001), with final outputs reaching 2.010 - a 70.4% improvement. Refined slogans are 48.4% shorter, 40.7% more novel, with only a 4.0% drop in relevance. Cross-modal tests show strong slogan-to-image alignment (CLIPScore: 0.249; BERTScore F1: 0.816). In human evaluations, the generated outputs were consistently rated highly, demonstrating strong creative quality and expressive clarity. Feedback highlights stylistic precision and emotional resonance. These results demonstrate that error-centered, feedback-driven generation enhances creativity, offering a scalable path toward self-evolving, human-aligned creative AI.
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。