CookingSense: A Culinary Knowledgebase with Multidisciplinary Assertions

TL;DR

CookingSense is a comprehensive culinary knowledgebase created from diverse sources, enhancing retrieval models and supporting culinary decision-making through a new benchmark and semantic filtering techniques.

Contribution

The paper introduces CookingSense, a multidisciplinary culinary knowledgebase, and FoodBench, a benchmark for evaluating culinary decision support systems, with novel filtering methods.

Findings

CookingSense improves retrieval augmented language model performance.

FoodBench effectively evaluates culinary decision support systems.

Qualitative analysis confirms the quality and diversity of assertions.

Abstract

This paper introduces CookingSense, a descriptive collection of knowledge assertions in the culinary domain extracted from various sources, including web data, scientific papers, and recipes, from which knowledge covering a broad range of aspects is acquired. CookingSense is constructed through a series of dictionary-based filtering and language model-based semantic filtering techniques, which results in a rich knowledgebase of multidisciplinary food-related assertions. Additionally, we present FoodBench, a novel benchmark to evaluate culinary decision support systems. From evaluations with FoodBench, we empirically prove that CookingSense improves the performance of retrieval augmented language models. We also validate the quality and variety of assertions in CookingSense through qualitative analysis.