# Counterfactual Recipe Generation: Exploring Compositional Generalization in a Realistic Scenario

arXiv: https://arxiv.org/abs/2210.11431 · HTML: https://mlsanity.com/paper/2210.11431/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 39 references that are in the map.
- First posted on arXiv 20 Oct 2022.

## Builds on (most cited first, 22 of 22)

- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning](https://mlsanity.com/paper/1612.06890/) (2016)
- [Measuring Compositional Generalization: A Comprehensive Method on Realistic Data](https://mlsanity.com/paper/1912.09713/) (2019)
- [COGS: A Compositional Generalization Challenge Based on Semantic Interpretation](https://mlsanity.com/paper/2010.05465/) (2020)
- [Compositional Generalization and Natural Language Variation: Can a Semantic Parsing Approach Handle Both?](https://mlsanity.com/paper/2010.12725/) (2020)
- [A Benchmark for Systematic Generalization in Grounded Language Understanding](https://mlsanity.com/paper/2003.05161/) (2020)
- [Compositional generalization through meta sequence-to-sequence learning](https://mlsanity.com/paper/1906.05381/) (2019)
- [Counterfactual Story Reasoning and Generation](https://mlsanity.com/paper/1909.04076/) (2019)
- [Best-Worst Scaling More Reliable than Rating Scales: A Case Study on Sentiment Intensity Annotation](https://mlsanity.com/paper/1712.01765/) (2017)
- [Learning Compositional Rules via Neural Program Synthesis](https://mlsanity.com/paper/2003.05562/) (2020)
- [Back to the Future: Unsupervised Backprop-based Decoding for Counterfactual and Abductive Commonsense Reasoning](https://mlsanity.com/paper/2010.05906/) (2020)
- [UER: An Open-Source Toolkit for Pre-training Models](https://mlsanity.com/paper/1909.05658/) (2019)
- [Broaden the Vision: Geo-Diverse Visual Commonsense Reasoning](https://mlsanity.com/paper/2109.06860/) (2021)
- [Simulating Action Dynamics with Neural Process Networks](https://mlsanity.com/paper/1711.05313/) (2017)
- [Generating Personalized Recipes from Historical User Preferences](https://mlsanity.com/paper/1909.00105/) (2019)
- [CLUECorpus2020: A Large-scale Chinese Corpus for Pre-training Language Model](https://mlsanity.com/paper/2003.01355/) (2020)
- [RecipeGPT: Generative Pre-training Based Cooking Recipe Generation and Evaluation System](https://mlsanity.com/paper/2003.02498/) (2020)
- [Multi-modal Cooking Workflow Construction for Food Recipes](https://mlsanity.com/paper/2008.09151/) (2020)
- [SHARE: a System for Hierarchical Assistive Recipe Editing](https://mlsanity.com/paper/2105.08185/) (2021)
- [Unsupervised Editing for Counterfactual Stories](https://mlsanity.com/paper/2112.05417/) (2021)
- [Evaluating Recipes Generated from Functional Object-Oriented Network](https://mlsanity.com/paper/2106.00728/) (2021)
- [Assistive Recipe Editing through Critiquing](https://mlsanity.com/paper/2205.02454/) (2022)

## Built on by (most cited first, 5 of 5)

- [FoodieQA: A Multimodal Dataset for Fine-Grained Understanding of Chinese Food Culture](https://mlsanity.com/paper/2406.11030/) (2024)
- [Cultural Adaptation of Menus: A Fine-Grained Approach](https://mlsanity.com/paper/2408.13534/) (2024)
- [Cultural Adaptation of Recipes](https://mlsanity.com/paper/2310.17353/) (2023)
- [DiNeR: a Large Realistic Dataset for Evaluating Compositional Generalization](https://mlsanity.com/paper/2406.04669/) (2024)
- [Epicure: Navigating the Emergent Geometry of Food Ingredient Embeddings](https://mlsanity.com/paper/2605.22391/) (2026)

## Abstract (arXiv)

People can acquire knowledge in an unsupervised manner by reading, and compose the knowledge to make novel combinations. In this paper, we investigate whether pretrained language models can perform compositional generalization in a realistic setting: recipe generation. We design the counterfactual recipe generation task, which asks models to modify a base recipe according to the change of an ingredient. This task requires compositional generalization at two levels: the surface level of incorporating the new ingredient into the base recipe, and the deeper level of adjusting actions related to the changing ingredient. We collect a large-scale recipe dataset in Chinese for models to learn culinary knowledge, and a subset of action-level fine-grained annotations for evaluation. We finetune pretrained language models on the recipe corpus, and use unsupervised counterfactual generation methods to generate modified recipes. 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. Although pretrained language models can generate fluent recipe texts, they fail to truly learn and use the culinary knowledge in a compositional way. Code and data are available at https://github.com/xxxiaol/counterfactual-recipe-generation.