On Recipe Memorization and Creativity in Large Language Models: Is Your Model a Creative Cook, a Bad Cook, or Merely a Plagiator?

• URL: http://arxiv.org/abs/2506.23527v1
• Date: Mon, 30 Jun 2025 05:27:11 GMT
• Title: On Recipe Memorization and Creativity in Large Language Models: Is Your Model a Creative Cook, a Bad Cook, or Merely a Plagiator?
• Authors: Jan Kvapil, Martin Fajcik,
• Abstract summary: This work-in-progress investigates the memorization, creativity, and nonsense found in cooking recipes generated from Large Language Models.<n>We design an LLM-as-judge'' pipeline that automates recipe generation, nonsense detection, parsing ingredients and recipe steps, and their annotation.
• Score: 1.7665640642293559
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: This work-in-progress investigates the memorization, creativity, and nonsense found in cooking recipes generated from Large Language Models (LLMs). Precisely, we aim (i) to analyze memorization, creativity, and non-sense in LLMs using a small, high-quality set of human judgments and (ii) to evaluate potential approaches to automate such a human annotation in order to scale our study to hundreds of recipes. To achieve (i), we conduct a detailed human annotation on 20 preselected recipes generated by LLM (Mixtral), extracting each recipe's ingredients and step-by-step actions to assess which elements are memorized--i.e., directly traceable to online sources possibly seen during training--and which arise from genuine creative synthesis or outright nonsense. We find that Mixtral consistently reuses ingredients that can be found in online documents, potentially seen during model training, suggesting strong reliance on memorized content. To achieve aim (ii) and scale our analysis beyond small sample sizes and single LLM validation, we design an ``LLM-as-judge'' pipeline that automates recipe generation, nonsense detection, parsing ingredients and recipe steps, and their annotation. For instance, comparing its output against human annotations, the best ingredient extractor and annotator is Llama 3.1+Gemma 2 9B, achieving up to 78% accuracy on ingredient matching. This automated framework enables large-scale quantification of memorization, creativity, and nonsense in generated recipes, providing rigorous evidence of the models' creative capacities.

Related papers

• 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)
• Deep Learning Based Named Entity Recognition Models for Recipes [7.507956305171027]
  Named entity recognition (NER) is a technique for extracting information from unstructured or semi-structured data with known labels. We created an augmented dataset of 26,445 phrases cumulatively. We analyzed ingredient phrases from RecipeDB, the gold-standard recipe data repository, and annotated them using the Stanford NER. A thorough investigation of NER approaches on these datasets involving statistical, fine-tuning of deep learning-based language models provides deep insights.
  arXiv  Detail & Related papers  (2024-02-27T12:03:56Z)
• Large Language Models as Sous Chefs: Revising Recipes with GPT-3 [56.7155146252028]
  We focus on recipes as an example of complex, diverse, and widely used instructions. We develop a prompt grounded in the original recipe and ingredients list that breaks recipes down into simpler steps. We also contribute an Amazon Mechanical Turk task that is carefully designed to reduce fatigue while collecting human judgment of the quality of recipe revisions.
  arXiv  Detail & Related papers  (2023-06-24T14:42:43Z)
• 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)
• 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)
• Revamping Cross-Modal Recipe Retrieval with Hierarchical Transformers and Self-supervised Learning [17.42688184238741]
  Cross-modal recipe retrieval has recently gained substantial attention due to the importance of food in people's lives. We propose a simplified end-to-end model based on well established and high performing encoders for text and images. Our proposed method achieves state-of-the-art performance in the cross-modal recipe retrieval task on the Recipe1M dataset.
  arXiv  Detail & Related papers  (2021-03-24T10:17:09Z)
• Structure-Aware Generation Network for Recipe Generation from Images [142.047662926209]
  We investigate an open research task of generating cooking instructions based on only food images and ingredients. Target recipes are long-length paragraphs and do not have annotations on structure information. We propose a novel framework of Structure-aware Generation Network (SGN) to tackle the food recipe generation task.
  arXiv  Detail & Related papers  (2020-09-02T10:54:25Z)
• Multi-modal Cooking Workflow Construction for Food Recipes [147.4435186953995]
  We build MM-ReS, the first large-scale dataset for cooking workflow construction. We propose a neural encoder-decoder model that utilizes both visual and textual information to construct the cooking workflow.
  arXiv  Detail & Related papers  (2020-08-20T18:31:25Z)

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.