Cooking Up Creativity: Enhancing LLM Creativity through Structured Recombination
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866911180442828800 |
|---|---|
| author | Mizrahi, Moran Shani, Chen Stanovsky, Gabriel Jurafsky, Dan Shahaf, Dafna |
| author_facet | Mizrahi, Moran Shani, Chen Stanovsky, Gabriel Jurafsky, Dan Shahaf, Dafna |
| contents | Large Language Models (LLMs) excel at many tasks, yet they struggle to produce truly creative, diverse ideas. In this paper, we introduce a novel approach that enhances LLM creativity. We apply LLMs for translating between natural language and structured representations, and perform the core creative leap via cognitively inspired manipulations on these representations. Our notion of creativity goes beyond superficial token-level variations; rather, we recombine structured representations of existing ideas, enabling our system to effectively explore a more abstract landscape of ideas. We demonstrate our approach in the culinary domain with DishCOVER, a model that generates creative recipes. Experiments and domain-expert evaluations reveal that our outputs, which are mostly coherent and feasible, significantly surpass GPT-4o in terms of novelty and diversity, thus outperforming it in creative generation. We hope our work inspires further research into structured creativity in AI. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_20643 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Cooking Up Creativity: Enhancing LLM Creativity through Structured Recombination Mizrahi, Moran Shani, Chen Stanovsky, Gabriel Jurafsky, Dan Shahaf, Dafna Computation and Language Artificial Intelligence Machine Learning Large Language Models (LLMs) excel at many tasks, yet they struggle to produce truly creative, diverse ideas. In this paper, we introduce a novel approach that enhances LLM creativity. We apply LLMs for translating between natural language and structured representations, and perform the core creative leap via cognitively inspired manipulations on these representations. Our notion of creativity goes beyond superficial token-level variations; rather, we recombine structured representations of existing ideas, enabling our system to effectively explore a more abstract landscape of ideas. We demonstrate our approach in the culinary domain with DishCOVER, a model that generates creative recipes. Experiments and domain-expert evaluations reveal that our outputs, which are mostly coherent and feasible, significantly surpass GPT-4o in terms of novelty and diversity, thus outperforming it in creative generation. We hope our work inspires further research into structured creativity in AI. |
| title | Cooking Up Creativity: Enhancing LLM Creativity through Structured Recombination |
| topic | Computation and Language Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2504.20643 |