A Highly Clean Recipe Dataset with Ingredient States Annotation for State Probing Task

• URL: http://arxiv.org/abs/2507.17232v1
• Date: Wed, 23 Jul 2025 05:56:20 GMT
• Title: A Highly Clean Recipe Dataset with Ingredient States Annotation for State Probing Task
• Authors: Mashiro Toyooka, Kiyoharu Aizawa, Yoko Yamakata,
• Abstract summary: We propose a new task and dataset for evaluating how well language models can recognize intermediate ingredient states during cooking procedures.<n>We first construct a new Japanese recipe dataset with clear and accurate annotations of ingredient state changes.<n>Using this dataset, we design three novel tasks to evaluate whether LLMs can track ingredient state transitions and identify ingredients present at intermediate steps.
• Score: 30.349846688239293
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large Language Models (LLMs) are trained on a vast amount of procedural texts, but they do not directly observe real-world phenomena. In the context of cooking recipes, this poses a challenge, as intermediate states of ingredients are often omitted, making it difficult for models to track ingredient states and understand recipes accurately. In this paper, we apply state probing, a method for evaluating a language model's understanding of the world, to the domain of cooking. We propose a new task and dataset for evaluating how well LLMs can recognize intermediate ingredient states during cooking procedures. We first construct a new Japanese recipe dataset with clear and accurate annotations of ingredient state changes, collected from well-structured and controlled recipe texts. Using this dataset, we design three novel tasks to evaluate whether LLMs can track ingredient state transitions and identify ingredients present at intermediate steps. Our experiments with widely used LLMs, such as Llama3.1-70B and Qwen2.5-72B, show that learning ingredient state knowledge improves their understanding of cooking processes, achieving performance comparable to commercial LLMs.

Related papers

• OSCAR: Object Status and Contextual Awareness for Recipes to Support Non-Visual Cooking [24.6085205199758]
  Following recipes while cooking is an important but difficult task for visually impaired individuals.<n>We developed OSCAR, a novel approach that provides recipe progress tracking and context-aware feedback.<n>We evaluated OSCAR's recipe following functionality using 173 YouTube cooking videos and 12 real-world non-visual cooking videos.
  arXiv  Detail & Related papers  (2025-03-07T22:03:21Z)
• Retrieval Augmented Recipe Generation [96.43285670458803]
  We propose a retrieval augmented large multimodal model for recipe generation.<n>It retrieves recipes semantically related to the image from an existing datastore as a supplement.<n>It calculates the consistency among generated recipe candidates, which use different retrieval recipes as context for generation.
  arXiv  Detail & Related papers  (2024-11-13T15:58:50Z)
• LLaVA-Chef: A Multi-modal Generative Model for Food Recipes [17.705244174235045]
  Large language models (LLMs) have paved the way for Natural Language Processing approaches to delve deeper into food-related tasks. This work proposes LLaVA-Chef, a novel model trained on a curated dataset of diverse recipe prompts. A detailed qualitative analysis reveals that LLaVA-Chef generates more detailed recipes with precise ingredient mentions.
  arXiv  Detail & Related papers  (2024-08-29T20:20:49Z)
• PizzaCommonSense: Learning to Model Commonsense Reasoning about Intermediate Steps in Cooking Recipes [7.839338724237275]
  A model to effectively reason about cooking recipes must accurately discern and understand the inputs and outputs of intermediate steps within the recipe. We present a new corpus of cooking recipes enriched with descriptions of intermediate steps that describe the input and output for each step.
  arXiv  Detail & Related papers  (2024-01-12T23:33:01Z)
• Data-Juicer: A One-Stop Data Processing System for Large Language Models [73.27731037450995]
  A data recipe is a mixture of data from different sources for training Large Language Models (LLMs) We build a new system named Data-Juicer, with which we can efficiently generate diverse data recipes. The data recipes derived with Data-Juicer gain notable improvements on state-of-the-art LLMs.
  arXiv  Detail & Related papers  (2023-09-05T08:22:07Z)
• KitchenScale: Learning to predict ingredient quantities from recipe contexts [13.001618172288198]
  KitchenScale is a model that predicts a target ingredient's quantity and measurement unit given its recipe context. We formulate an ingredient quantity prediction task that consists of three sub-tasks which are ingredient measurement type classification, unit classification, and quantity regression task. Experiments with our newly constructed dataset and recommendation examples demonstrate KitchenScale's understanding of various recipe contexts.
  arXiv  Detail & Related papers  (2023-04-21T04:28:16Z)
• ICL-D3IE: In-Context Learning with Diverse Demonstrations Updating for Document Information Extraction [56.790794611002106]
  Large language models (LLMs) have demonstrated remarkable results in various natural language processing (NLP) tasks with in-context learning. We propose a simple but effective in-context learning framework called ICL-D3IE. Specifically, we extract the most difficult and distinct segments from hard training documents as hard demonstrations.
  arXiv  Detail & Related papers  (2023-03-09T06:24:50Z)
• Structured Vision-Language Pretraining for Computational Cooking [54.0571416522547]
  Vision-Language Pretraining and Foundation models have been the go-to recipe for achieving SoTA performance on general benchmarks. We propose to leverage these techniques for structured-text based computational cuisine tasks.
  arXiv  Detail & Related papers  (2022-12-08T13:37:17Z)
• Counterfactual Recipe Generation: Exploring Compositional Generalization in a Realistic Scenario [60.20197771545983]
  We design the counterfactual recipe generation task, which asks models to modify a base recipe according to the change of an ingredient. We collect a large-scale recipe dataset in Chinese for models to learn culinary knowledge. Results show that existing models have difficulties in modifying the ingredients while preserving the original text style, and often miss actions that need to be adjusted.
  arXiv  Detail & Related papers  (2022-10-20T17:21:46Z)
• Learning Structural Representations for Recipe Generation and Food Retrieval [101.97397967958722]
  We propose a novel framework of Structure-aware Generation Network (SGN) to tackle the food recipe generation task. Our proposed model can produce high-quality and coherent recipes, and achieve the state-of-the-art performance on the benchmark Recipe1M dataset.
  arXiv  Detail & Related papers  (2021-10-04T06:36:31Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.