paper-with-me

홈 › Papers

Cooking Up Creativity: A Cognitively-Inspired Approach for Enhancing LLM Creativity through Structured Representations

2025-04-29 · Moran Mizrahi, Chen Shani, Gabriel Stanovsky, Dan Jurafsky, Dafna Shahaf

Large Language Models (LLMs) excel at countless tasks, yet struggle with creativity. In this paper, we introduce a novel approach that couples LLMs with structured representations and cognitively inspired manipulations to generate more creative and diverse ideas. Our notion of creativity goes beyond superficial token-level variations; rather, we explicitly recombine structured representations of existing ideas, allowing our algorithm to effectively explore the more abstract landscape of ideas. We demonstrate our approach in the culinary domain with DishCOVER, a model that generates creative recipes. Experiments comparing our model's results to those of GPT-4o show greater diversity. Domain expert evaluations reveal that our outputs, which are mostly coherent and feasible culinary creations, significantly surpass GPT-4o in terms of novelty, thus outperforming it in creative generation. We hope our work inspires further research into structured creativity in AI.

📄 PDF Abstract BibTeX arXiv:2504.20643

Code (1)

moranmiz/Cooking-Up-Creativity 공식 구현

Tasks

Diversity

Similar Papers 제목 키워드 기반

Seeking the Building Blocks of Visual Imagery and Creativity in a Cognitively Inspired Neural Network

2021-12-13 · NeurIPS Workshop SVRHM 2021 12 · Shekoofeh Hedayati, Roger Beaty, Brad Wyble

How do we imagine visual objects and combine them to create new forms? To answer this question, we need to explore the cognitive, computational and neural mechanisms underlying imagery and creativity. The body of researc…

Stable diffusion models reveal a persisting human and AI gap in visual creativity

2025-11-20 · Silvia Rondini, Claudia Alvarez-Martin, Paula Angermair-Barkai, Olivier Penacchio 외 arxiv

While recent research suggests Large Language Models match human creative performance in divergent thinking tasks, visual creativity remains underexplored. This study compared image generation in human participants (Visu…

Image Generation

CIZSL++: Creativity Inspired Generative Zero-Shot Learning

2021-01-01 · Mohamed Elhoseiny, Kai Yi, Mohamed Elfeki

Zero-shot learning (ZSL) aims at understanding unseen categories with no training examples from class-level descriptions. To improve the discriminative power of ZSL, we model the visual learning process of unseen categor…

AttributeTransfer LearningZero-Shot Learning

CreativityNeuro: Steering Language Model Weights to Improve Divergent Thinking and Reduce Mode Collapse

2026-07-01 · Samuel Schapiro, Core Francisco Park, Felix Sosa, Lav R. Varshney arxiv

Divergent thinking is a crucial aspect of creativity, yet large language models (LLMs) tend to consistently generate similar responses to open-ended questions, in what has been termed the artificial hivemind effect. Here…

Interdisciplinary Methods in Computational Creativity: How Human Variables Shape Human-Inspired AI Research

2023-06-29 · Nadia M. Ady, Faun Rice

The word creativity originally described a concept from human psychology, but in the realm of computational creativity (CC), it has become much more. The question of what creativity means when it is part of a computation…