cs.AI updates on arXiv.org 07月25日 12:28
E.A.R.T.H.: Structuring Creative Evolution through Model Error in Generative AI
index_new5.html
../../../zaker_core/zaker_tpl_static/wap/tpl_guoji1.html

 

本文提出E.A.R.T.H.框架,通过五个阶段将模型错误转化为创意资产,运用认知科学和生成模型,实现从模仿到真正创造性的突破。

arXiv:2507.18004v1 Announce Type: new Abstract: 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 = 4.0, with metaphorical slogans (avg. 4.09) outperforming literal ones (3.99). 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.

Fish AI Reader

Fish AI Reader

AI辅助创作,多种专业模板,深度分析,高质量内容生成。从观点提取到深度思考,FishAI为您提供全方位的创作支持。新版本引入自定义参数,让您的创作更加个性化和精准。

FishAI

FishAI

鱼阅,AI 时代的下一个智能信息助手,助你摆脱信息焦虑

联系邮箱 441953276@qq.com

相关标签

AI创意 E.A.R.T.H.框架 生成模型 错误驱动
相关文章