PizzaCommonSense: Learning to Model Commonsense Reasoning about Intermediate Steps in Cooking Recipes
On the map: LLM reasoning → Reasoning benchmarks and evaluation
Abstract (arXiv)
Understanding procedural texts, such as cooking recipes, is essential for enabling machines to follow instructions and reason about tasks, a key aspect of intelligent reasoning. In cooking, these instructions can be interpreted as a series of modifications to a food preparation. For a model to effectively reason about cooking recipes, it 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. PizzaCommonsense serves as a benchmark for the reasoning capabilities of LLMs because it demands rigorous explicit input-output descriptions to demonstrate the acquisition of implicit commonsense knowledge, which is unlikely to be easily memorized. GPT-4 achieves only 26% human-evaluated preference for generations, leaving room for future improvements.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning. Builds on 22 of its 50 references that are in the map. First posted on arXiv 12 Jan 2024.
Builds on
22 of 50 references.
References · 22
- 2020Language Models are Few-Shot Learnerscited by 32,199
- 2023GPT-4 Technical Reportcited by 18,132
- 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
- 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,601
- 2019BERTScore: Evaluating Text Generation with BERTcited by 5,462
- 2022Large Language Models are Zero-Shot Reasonerscited by 4,323
- 2022Scaling Instruction-Finetuned Language Modelscited by 2,997
- 2022Least-to-Most Prompting Enables Complex Reasoning in Large Language Modelscited by 1,397
- 2021An Explanation of In-context Learning as Implicit Bayesian Inferencecited by 915
- 2021Deep Neural Networks and Tabular Data: A Surveycited by 489
- 2020TaBERT: Pretraining for Joint Understanding of Textual and Tabular Datacited by 395
- 2019Measuring Compositional Generalization: A Comprehensive Method on Realistic Datacited by 280
10 more
- 2020COGS: A Compositional Generalization Challenge Based on Semantic Interpretationcited by 260
- 2022Can Foundation Models Wrangle Your Data?cited by 173
- 2022Distilling Reasoning Capabilities into Smaller Language Modelscited by 155
- 2017Simulating Action Dynamics with Neural Process Networkscited by 53
- 2016Tracking the World State with Recurrent Entity Networkscited by 51
- 2021Text-to-Table: A New Way of Information Extractioncited by 47
- 2018Jump to better conclusions: SCAN both left and rightcited by 29
- 2019Tracking Discrete and Continuous Entity State for Process Understandingcited by 15
- 2019Effective Use of Transformer Networks for Entity Trackingcited by 11
- 2021CHEF: Cross-modal Hierarchical Embeddings for Food Domain Retrievalcited by 7
Built on by
Citing papers per year: 2024: 1; 2025: 1.
2 papers.
Similar, not cited
Close in wording, no citation either way
- 2023A Graphical Formalism for Commonsense Reasoning with Recipes
- 2026ReGraph: Learning to Generate Recipe Graphs from Food Images
- 2025Evaluating LLMs' Reasoning Over Ordered Procedural Steps
- 2026NutriBench-Kitchen: Benchmarking Embodied AI for Nutrition Management
- 2026Enhancing Action and Ingredient Modeling for Semantically Grounded Recipe Generation
- 2024CookingSense: A Culinary Knowledgebase with Multidisciplinary Assertions
- 2022Visual Recipe Flow: A Dataset for Learning Visual State Changes of Objects with Recipe Flows
- 2023STEPS: A Benchmark for Order Reasoning in Sequential Tasks