Culinary Crossroads: A RAG Framework for Enhancing Diversity in Cross-Cultural Recipe Adaptation

TL;DR

This paper introduces CARRIAGE, a RAG framework designed to improve diversity in cross-cultural recipe adaptation by addressing RAG's tendency to generate limited variations, thus better accommodating diverse user preferences.

Contribution

It presents the first RAG framework explicitly aimed at enhancing diversity in recipe adaptation, combining retrieval and context organization improvements.

Findings

CARRIAGE outperforms closed-book LLMs in diversity and quality.

RAG tends to rely on limited context, reducing output diversity.

CARRIAGE achieves Pareto efficiency in diversity and quality.

Abstract

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.