Large Language Models as Sous Chefs: Revising Recipes with GPT-3

• URL: http://arxiv.org/abs/2306.13986v1
• Date: Sat, 24 Jun 2023 14:42:43 GMT
• Title: Large Language Models as Sous Chefs: Revising Recipes with GPT-3
• Authors: Alyssa Hwang, Bryan Li, Zhaoyi Hou, Dan Roth
• Abstract summary: 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.
• Score: 56.7155146252028
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: With their remarkably improved text generation and prompting capabilities, large language models can adapt existing written information into forms that are easier to use and understand. In our work, 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 apply this prompt to recipes from various world cuisines, and experiment with several large language models (LLMs), finding best results with GPT-3.5. 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. We find that annotators usually prefer the revision over the original, demonstrating a promising application of LLMs in serving as digital sous chefs for recipes and beyond. We release our prompt, code, and MTurk template for public use.

Related papers

• 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)
• Monte Carlo Tree Search for Recipe Generation using GPT-2 [0.8057006406834466]
  We propose RecipeMC, a text generation method using GPT-2 that relies on Monte Carlo Tree Search (MCTS) RecipeMC allows us to define reward functions to put soft constraints on text generation and thus improve the credibility of the generated recipes. Our results show that human evaluators prefer recipes generated with RecipeMC more often than recipes generated with other baseline methods.
  arXiv  Detail & Related papers  (2024-01-10T14:50:46Z)
• 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)
• Recitation-Augmented Language Models [85.30591349383849]
  We show that RECITE is a powerful paradigm for knowledge-intensive NLP tasks. Specifically, we show that by utilizing recitation as the intermediate step, a recite-and-answer scheme can achieve new state-of-the-art performance.
  arXiv  Detail & Related papers  (2022-10-04T00:49:20Z)
• Assistive Recipe Editing through Critiquing [34.1050269670062]
  RecipeCrit is a hierarchical denoising auto-encoder that edits recipes given ingredient-level critiques. Our work's main innovation is our unsupervised critiquing module that allows users to edit recipes by interacting with the predicted ingredients.
  arXiv  Detail & Related papers  (2022-05-05T05:52:27Z)
• A Rich Recipe Representation as Plan to Support Expressive Multi Modal Queries on Recipe Content and Preparation Process [24.94173789568803]
  We discuss the construction of a machine-understandable rich recipe representation (R3) R3 is infused with additional knowledge such as information about allergens and images of ingredients. We also present TREAT, a tool for recipe retrieval which uses R3 to perform multi-modal reasoning on the recipe's content.
  arXiv  Detail & Related papers  (2022-03-31T15:29:38Z)
• 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)
• Decomposing Generation Networks with Structure Prediction for Recipe Generation [142.047662926209]
  We propose a novel framework: Decomposing Generation Networks (DGN) with structure prediction. Specifically, we split each cooking instruction into several phases, and assign different sub-generators to each phase. Our approach includes two novel ideas: (i) learning the recipe structures with the global structure prediction component and (ii) producing recipe phases in the sub-generator output component based on the predicted structure.
  arXiv  Detail & Related papers  (2020-07-27T08:47:50Z)
• A Recipe for Creating Multimodal Aligned Datasets for Sequential Tasks [48.39191088844315]
  In the cooking domain, the web offers many partially-overlapping text and video recipes that describe how to make the same dish. We use an unsupervised alignment algorithm that learns pairwise alignments between instructions of different recipes for the same dish. We then use a graph algorithm to derive a joint alignment between multiple text and multiple video recipes for the same dish.
  arXiv  Detail & Related papers  (2020-05-19T17:27:00Z)

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.