arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2604.22776cs.CYcs.AIcs.LG
收藏

Epicure:食品成分嵌入中的多维风味结构

Epicure: Multidimensional Flavor Structure in Food Ingredient Embeddings

Jakub Radzikowski, Josef Chen

AI总结:

本文通过FlavorGraph的300维嵌入揭示了风味、质地、地理和文化等多维风味结构,并通过LLM增强的管道整合了6653种原料,提升了可恢复结构。

摘要:

厨师对风味、质地和文化身份的直觉知识是难以言说却对烹饪实践至关重要的隐性知识。我们证明这种知识已编码在FlavorGraph的300维成分嵌入中,该嵌入基于食谱共现和食品化学训练,并能系统性地恢复。一个增强的LLM管道将6653种原始FlavorGraph成分整合为1032种标准条目,显著增强了可恢复结构。我们识别出至少十五个独立可分类的维度,涵盖味道、质地、地理、食品加工和文化。

英文摘要:

A chef's intuition about flavor, texture, and cultural identity represents tacit knowledge that is difficult to articulate yet central to culinary practice. We show that this knowledge is already encoded in FlavorGraph's 300-dimensional ingredient embeddings, trained on recipe cooccurrence and food chemistry, and that it can be systematically recovered. An LLM-augmented curation pipeline consolidates 6,653 raw FlavorGraph ingredients into 1,032 canonical entries, substantially strengthening the recoverable structure. We identify at least fifteen independently classifiable dimensions spanning taste, texture, geography, food processing, and culture.

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。

↑