Culinary Crossroads: A RAG Framework for Enhancing Diversity in Cross-Cultural Recipe Adaptation
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866917418881777664 |
|---|---|
| author | Hu, Tianyi Morales-Garzón, Andrea Zheng, Jingyi Maistro, Maria Hershcovich, Daniel |
| author_facet | Hu, Tianyi Morales-Garzón, Andrea Zheng, Jingyi Maistro, Maria Hershcovich, Daniel |
| contents | In cross-cultural recipe adaptation, the goal is not only to ensure cultural appropriateness and retain the original dish's essence, but also to provide diverse options for various dietary needs and preferences. Retrieval Augmented Generation (RAG) is a promising approach, combining the retrieval of real recipes from the target cuisine for cultural adaptability with large language models (LLMs) for relevance. However, it remains unclear whether RAG can generate diverse adaptation results. Our analysis shows that RAG tends to overly rely on a limited portion of the context across generations, failing to produce diverse outputs even when provided with varied contextual inputs. This reveals a key limitation of RAG in creative tasks with multiple valid answers: it fails to leverage contextual diversity for generating varied responses. To address this issue, we propose CARRIAGE, a plug-and-play RAG framework for cross-cultural recipe adaptation that enhances diversity in both retrieval and context organization. To our knowledge, this is the first RAG framework that explicitly aims to generate highly diverse outputs to accommodate multiple user preferences. Our experiments show that CARRIAGE achieves Pareto efficiency in terms of diversity and quality of recipe adaptation compared to closed-book LLMs. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_21934 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Culinary Crossroads: A RAG Framework for Enhancing Diversity in Cross-Cultural Recipe Adaptation Hu, Tianyi Morales-Garzón, Andrea Zheng, Jingyi Maistro, Maria Hershcovich, Daniel Computation and Language Artificial Intelligence Computers and Society Information Retrieval Machine Learning In cross-cultural recipe adaptation, the goal is not only to ensure cultural appropriateness and retain the original dish's essence, but also to provide diverse options for various dietary needs and preferences. Retrieval Augmented Generation (RAG) is a promising approach, combining the retrieval of real recipes from the target cuisine for cultural adaptability with large language models (LLMs) for relevance. However, it remains unclear whether RAG can generate diverse adaptation results. Our analysis shows that RAG tends to overly rely on a limited portion of the context across generations, failing to produce diverse outputs even when provided with varied contextual inputs. This reveals a key limitation of RAG in creative tasks with multiple valid answers: it fails to leverage contextual diversity for generating varied responses. To address this issue, we propose CARRIAGE, a plug-and-play RAG framework for cross-cultural recipe adaptation that enhances diversity in both retrieval and context organization. To our knowledge, this is the first RAG framework that explicitly aims to generate highly diverse outputs to accommodate multiple user preferences. Our experiments show that CARRIAGE achieves Pareto efficiency in terms of diversity and quality of recipe adaptation compared to closed-book LLMs. |
| title | Culinary Crossroads: A RAG Framework for Enhancing Diversity in Cross-Cultural Recipe Adaptation |
| topic | Computation and Language Artificial Intelligence Computers and Society Information Retrieval Machine Learning |
| url | https://arxiv.org/abs/2507.21934 |