Browse State-of-the-Art › Recipe Generation

Recipe Generation

15 papers with code · 5 benchmarks · 3 datasets archive 2025-07-28

MiscellaneousNatural Language Processing

Food recipe generation from ingredients, title and/or food images.

Description from the archive archive 2025-07-28.

Benchmarks archive 2025-07-28

5 leaderboard tables shown for this task, 5 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted.

DatasetBest model (first row in archive order)PaperCodeSyntologyCompare
allrecipes.com (2 rows) Latent Variable Model Reference-Aware Language Models — — Compare
Food.com (2 rows) LLaVA-Chef LLaVA-Chef: A Multi-modal Generative Model for Food Recipes code — Compare
Now You're Cooking! (2 rows) LLaVA-Chef LLaVA-Chef: A Multi-modal Generative Model for Food Recipes code — Compare
Recipe1M (1 row) Set Transformer Inverse Cooking: Recipe Generation from Food Images code — Compare
RecipeNLG (1 row) GPT2-small RecipeNLG: A Cooking Recipes Dataset for Semi-Structured Text Generation code — Compare

Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. Each line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the row's paper, the line starts with that repository's state (“official” is the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from. A dash means no Syntology record for that paper, not a recorded non-run. Each “ran” line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.

Libraries

Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.

Datasets archive 2025-07-28

3 datasets whose archive record lists this task, ordered by the archive's paper count.

Subtasks archive 2025-07-28

No subtask under this task in the archive's task tree.

Papers archive 2025-07-28

archive papers tagged: 40 · with a code link: 15 · where Syntology ran a sample: 1 (1 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument) Syntology

Show: all tagged papersonly where code ran (1 of 40 tagged: 1 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument)

Page 1 of 1: papers 1 to 40 of 40, in archive order: by repositories listed in the archive (most first), then newest first, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers that list no repository come after every paper that lists one.

Papers without a page here are shown as plain text. A Syntology line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the figure “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code); hover it for the repositories the samples that ran came from. The first sentence of the abstract is shown for the first 30 papers; every abstract is on its paper's page.

  • 14 Dec 2018 4 repositories listed
    Our system predicts ingredients as sets by means of a novel architecture, modeling their dependencies without imposing any order, and then generates cooking instructions by attending to both image and its inferred…
  • 17 Apr 2023 2 repositories listed
    We generate instructions via LLMs for human-written corpus examples using reverse instructions.
  • 13 May 2018 2 repositories listed Syntology official: harvested, nothing ran · 0 ran · 1 unverified (of 1 harvested sample)
    Text in many domains involves a significant amount of named entities.
  • 20 May 2025 1 repository listed
    We introduce KERL, a unified system that leverages food KGs and LLMs to provide personalized food recommendations and generates recipes with associated micro-nutritional information.
  • 21 Sep 2024 1 repository listed
    Instruction tuning commonly means finetuning a language model on instruction-response pairs.
  • 18 Sep 2024 1 repository listed
    Significant work has been conducted in the domain of food computing, yet these studies typically focus on single tasks such as t2t (instruction generation from food titles and ingredients), i2t (recipe generation from…
  • 29 Aug 2024 1 repository listed
    This work evaluates existing LLMs for recipe generation and proposes LLaVA-Chef, a novel model trained on a curated dataset of diverse recipe prompts in a multi-stage approach.
  • Food computing has emerged as a prominent multidisciplinary field of research in recent years.
  • 15 Feb 2023 1 repository listed
    Recipe personalization through ingredient substitution has the potential to help people meet their dietary needs and preferences, avoid potential allergens, and ease culinary exploration in everyone's kitchen.
  • 20 Oct 2022 1 repository listed
    Although pretrained language models can generate fluent recipe texts, they fail to truly learn and use the culinary knowledge in a compositional way.
  • 17 May 2021 1 repository listed
    The large population of home cooks with dietary restrictions is under-served by existing cooking resources and recipe generation models.
  • 15 Dec 2020 1 repository listed
    We use the dataset to approach the problem of generating recipes.
  • 2 Sep 2020 1 repository listed
    We investigate an open research task of generating cooking instructions based on only food images and ingredients, which is similar to the image captioning task.
  • 5 Mar 2020 1 repository listed
    Interests in the automatic generation of cooking recipes have been growing steadily over the past few years thanks to a large amount of online cooking recipes.
  • 31 Aug 2019 1 repository listed
    Existing approaches to recipe generation are unable to create recipes for users with culinary preferences but incomplete knowledge of ingredients in specific dishes.
  • RecipeGen: A Step-Aligned Multimodal Benchmark for Real-World Recipe Generation
    7 Jun 2025 0 repositories listed
    Creating recipe images is a key challenge in food computing, with applications in culinary education and multimodal recipe assistants.
  • Few-Shot Test-Time Optimization Without Retraining for Semiconductor Recipe Generation and Beyond
    21 May 2025 0 repositories listed
    We introduce Model Feedback Learning (MFL), a novel test-time optimization framework for optimizing inputs to pre-trained AI models or deployed hardware systems without requiring any retraining of the models or…
  • Fine-tuning Language Models for Recipe Generation: A Comparative Analysis and Benchmark Study
    4 Feb 2025 0 repositories listed
    This research presents an exploration and study of the recipe generation task by fine-tuning various very small language models, with a focus on developing robust evaluation metrics and comparing across different…
  • Retrieval Augmented Recipe Generation
    13 Nov 2024 0 repositories listed
    Given the potential applications of generating recipes from food images, this area has garnered significant attention from researchers in recent years.
  • Culinary Class Wars: Evaluating LLMs using ASH in Cuisine Transfer Task
    4 Nov 2024 0 repositories listed
    The advent of Large Language Models (LLMs) have shown promise in various creative domains, including culinary arts.
  • FoodMLLM-JP: Leveraging Multimodal Large Language Models for Japanese Recipe Generation
    27 Sep 2024 0 repositories listed
    Research on food image understanding using recipe data has been a long-standing focus due to the diversity and complexity of the data.
  • Towards Automated Solution Recipe Generation for Industrial Asset Management with LLM
    26 Jul 2024 0 repositories listed
    This study introduces a novel approach to Industrial Asset Management (IAM) by incorporating Conditional-Based Management (CBM) principles with the latest advancements in Large Language Models (LLMs).
  • Deep Learning Based Named Entity Recognition Models for Recipes
    27 Feb 2024 0 repositories listed
    Food touches our lives through various endeavors, including flavor, nourishment, health, and sustainability.
  • Monte Carlo Tree Search for Recipe Generation using GPT-2
    10 Jan 2024 0 repositories listed
    Automatic food recipe generation methods provide a creative tool for chefs to explore and to create new, and interesting culinary delights.
  • FoodLMM: A Versatile Food Assistant using Large Multi-modal Model
    22 Dec 2023 0 repositories listed
    Large Multi-modal Models (LMMs) have made impressive progress in many vision-language tasks.
  • Towards Automated Recipe Genre Classification using Semi-Supervised Learning
    24 Oct 2023 0 repositories listed
    Sharing cooking recipes is a great way to exchange culinary ideas and provide instructions for food preparation.
  • Assorted, Archetypal and Annotated Two Million (3A2M) Cooking Recipes Dataset based on Active Learning
    27 Mar 2023 0 repositories listed
    Cooking recipes allow individuals to exchange culinary ideas and provide food preparation instructions.
  • Plug-and-Play Recipe Generation with Content Planning
    9 Dec 2022 0 repositories listed
    Recent pre-trained language models have shown promising capabilities in generating fluent and realistic natural language text.
  • FOON Creation and Traversal for Recipe Generation
    13 Oct 2022 0 repositories listed
    Task competition by robots is still off from being completely dependable and usable.
  • A generative grammar of cooking
    12 Oct 2022 0 repositories listed
    Cooking is a uniquely human endeavor for transforming raw ingredients into delicious dishes.
  • Towards Fine-Dining Recipe Generation with Generative Pre-trained Transformers
    26 Sep 2022 0 repositories listed
  • Recipe Generation from Unsegmented Cooking Videos
    21 Sep 2022 0 repositories listed
  • Ratatouille: A tool for Novel Recipe Generation
    10 May 2022 0 repositories listed
  • Learning Structural Representations for Recipe Generation and Food Retrieval
    4 Oct 2021 0 repositories listed
  • Building Hierarchically Disentangled Language Models for Text Generation with Named Entities
    1 Dec 2020 0 repositories listed
  • Routing Enforced Generative Model for Recipe Generation
    1 Nov 2020 0 repositories listed
  • Decomposing Generation Networks with Structure Prediction for Recipe Generation
    27 Jul 2020 0 repositories listed
  • Set to Ordered Text: Generating Discharge Instructions from Medical Billing Codes
    1 Nov 2019 0 repositories listed
  • 5 Nov 2016 0 repositories listed
  • Globally Coherent Text Generation with Neural Checklist Models
    1 Nov 2016 0 repositories listed

Syntology lines on 2 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced; each line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections