# CommonGen: A Constrained Text Generation Challenge for Generative Commonsense Reasoning

arXiv: https://arxiv.org/abs/1911.03705 · HTML: https://mlsanity.com/paper/1911.03705/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Nov 2019.

## Built on by (most cited first, 12 of 12)

- [CRASS: A Novel Data Set and Benchmark to Test Counterfactual Reasoning of Large Language Models](https://mlsanity.com/paper/2112.11941/) (2021)
- [Assessing Judging Bias in Large Reasoning Models: An Empirical Study](https://mlsanity.com/paper/2504.09946/) (2025)
- [Neural Pipeline for Zero-Shot Data-to-Text Generation](https://mlsanity.com/paper/2203.16279/) (2022)
- [Why is constrained neural language generation particularly challenging?](https://mlsanity.com/paper/2206.05395/) (2022)
- [GraphPlanner: Graph Memory-Augmented Agentic Routing for Multi-Agent LLMs](https://mlsanity.com/paper/2604.23626/) (2026)
- [Constrained Text Generation with Global Guidance -- Case Study on CommonGen](https://mlsanity.com/paper/2103.07170/) (2021)
- [TabGenie: A Toolkit for Table-to-Text Generation](https://mlsanity.com/paper/2302.14169/) (2023)
- [When LLMs Learn to be Students: The SOEI Framework for Modeling and Evaluating Virtual Student Agents in Educational Interaction](https://mlsanity.com/paper/2410.15701/) (2024)
- [Sibylvariant Transformations for Robust Text Classification](https://mlsanity.com/paper/2205.05137/) (2022)
- [Generative Adversarial Imitation Learning for Empathy-based AI](https://mlsanity.com/paper/2105.13328/) (2021)
- [Infusing Commonsense World Models with Graph Knowledge](https://mlsanity.com/paper/2301.05746/) (2023)
- [Making Bias Non-Predictive: Training Robust LLM Reasoning via Reinforcement Learning](https://mlsanity.com/paper/2602.01528/) (2026)

## Abstract (arXiv)

Recently, large-scale pre-trained language models have demonstrated impressive performance on several commonsense-reasoning benchmark datasets. However, building machines with commonsense to compose realistically plausible sentences remains challenging. In this paper, we present a constrained text generation task, CommonGen associated with a benchmark dataset, to explicitly test machines for the ability of generative commonsense reasoning. Given a set of common concepts (e.g., {dog, frisbee, catch, throw}); the task is to generate a coherent sentence describing an everyday scenario using these concepts (e.g., "a man throws a frisbee and his dog catches it"). The CommonGen task is challenging because it inherently requires 1) relational reasoning with background commonsense knowledge, and 2) compositional generalization ability to work on unseen concept combinations. Our dataset, constructed through a combination of crowdsourced and existing caption corpora, consists of 79k commonsense descriptions over 35k unique concept-sets. Experiments show that there is a large gap between state-of-the-art text generation models (e.g., T5) and human performance. Furthermore, we demonstrate that the learned generative commonsense reasoning capability can be transferred to improve downstream tasks such as CommonsenseQA by generating additional context.