Creative Priming:將創作過程與作品分離,以擺脱創意悖論
Creative Priming: Decoupling Process from Product to Escape the Creative Paradox
Creative priming 提出以 GRPO 訓練 priming model,按提示詞生成專屬 primer,協助 response model 產生新穎、高質素且多元的回應。此方法將創作過程與回應生成分開,透過獎勵能帶來理想回應的 primer,學習創作原則而非重複特定作品。
Published on Nov 9
Authors:
,
,
,
Abstract
A method called creative priming uses a priming model trained with GRPO to generate prompt-specific primers that help a response model produce novel, high-quality, and diverse outputs by separating the creative process from response generation.
Many of the most consequential advances promised by AI, from curing diseases and inventing new technologies to formulating new scientific theories, are fundamentally creative acts. Yet creativity is uniquely difficult to learn because it faces a creative paradox: learning to repeat past examples of creative success makes those specific examples more likely to recur, inhibiting the very creativity desired. This work argues that creativity is better modeled as an explicit process rather than as a property of individual artifacts, and proposes to learn the underlying generative principles behind the creative process. In particular, to escape the paradox, we introduce creative priming (CP), wherein a trained priming model generates a prompt-specific primer that assists a response model in being creative, explicitly decoupling the creative process from response generation. The priming model learns through GRPO, rewarding primers that lead to responses that are novel, high-quality, and diverse, thereby reinforcing the process that yields creative responses without reinforcing any specific response.
View arXiv page View PDF Add to collection
Get this paper in your agent:
hf papers read 2611.11740
Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash
Models citing this paper 0
No model linking this paper
Cite arxiv.org/abs/2611.11740 in a model README.md to link it from this page.
Datasets citing this paper 2
LilaSciences/infinite-chats-scored
Viewer • Updated about 1 hour ago • 26.1k • 2
LilaSciences/novelty-bench-llm-judge
Viewer • Updated about 1 hour ago • 100 • 2
Spaces citing this paper 0
No Space linking this paper
Cite arxiv.org/abs/2611.11740 in a Space README.md to link it from this page.
Collections including this paper 0
No Collection including this paper
Add this paper to a collection to link it from this page.
來源:HuggingFace Daily Papers(社區熱門論文) · huggingface.co