烹饪交汇点：一种增强跨文化食谱适应多样性的RAG框架
Culinary Crossroads: A RAG Framework for Enhancing Diversity in Cross-Cultural Recipe Adaptation
AI总结：
本文提出CARRIAGE框架，通过增强检索与上下文组织来提升跨文化食谱适应的多样性，解决了RAG在生成多样化结果时的局限性。
摘要：
在跨文化食谱适应中，目标不仅是确保文化适宜性和保留原菜的本质，还要提供多样化的选项以满足各种饮食需求和偏好。检索增强生成（RAG）是一种有前景的方法，结合了从目标菜系检索真实食谱以确保文化适应性与大型语言模型（LLMs）的相关性。然而，RAG是否能生成多样化的适应结果仍不明确。我们的分析表明，RAG倾向于过度依赖上下文中的有限部分，即使在提供多样化上下文输入的情况下，也无法生成多样化的输出。这揭示了RAG在具有多个有效答案的创造性任务中的关键局限性：它未能利用上下文多样性来生成多样化响应。为了解决这一问题，我们提出了CARRIAGE，一种用于跨文化食谱适应的即插即用RAG框架，旨在增强检索和上下文组织的多样性。据我们所知，这是第一个明确旨在生成高度多样化输出以满足多种用户需求的RAG框架。我们的实验表明，CARRIAGE在多样性和食谱适应质量方面实现了帕累托效率，优于封闭书本LLMs。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
