# Infusing Commonsense World Models with Graph Knowledge

arXiv: https://arxiv.org/abs/2301.05746 · HTML: https://mlsanity.com/paper/2301.05746/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in World models for language agents, one of 11 directions in World models.
- Builds on 15 of its 18 references that are in the map.
- First posted on arXiv 13 Jan 2023.

## Placed in

- World models / [World models for language agents](https://mlsanity.com/wm/world-models-for-language-agents/)

## Builds on (most cited first, 15 of 15)

- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [HellaSwag: Can a Machine Really Finish Your Sentence?](https://mlsanity.com/paper/1905.07830/) (2019)
- [Sequence to Sequence Learning with Neural Networks](https://mlsanity.com/paper/1409.3215/) (2014)
- [SWAG: A Large-Scale Adversarial Dataset for Grounded Commonsense Inference](https://mlsanity.com/paper/1808.05326/) (2018)
- [TextWorld: A Learning Environment for Text-based Games](https://mlsanity.com/paper/1806.11532/) (2018)
- [Queens are Powerful too: Mitigating Gender Bias in Dialogue Generation](https://mlsanity.com/paper/1911.03842/) (2019)
- [ParlAI: A Dialog Research Software Platform](https://mlsanity.com/paper/1705.06476/) (2017)
- [Learning to Speak and Act in a Fantasy Text Adventure Game](https://mlsanity.com/paper/1903.03094/) (2019)
- [KG-BART: Knowledge Graph-Augmented BART for Generative Commonsense Reasoning](https://mlsanity.com/paper/2009.12677/) (2020)
- [PIGLeT: Language Grounding Through Neuro-Symbolic Interaction in a 3D World](https://mlsanity.com/paper/2106.00188/) (2021)
- [Toward Automated Quest Generation in Text-Adventure Games](https://mlsanity.com/paper/1909.06283/) (2019)
- [CommonGen: A Constrained Text Generation Challenge for Generative Commonsense Reasoning](https://mlsanity.com/paper/1911.03705/) (2019)
- [Modeling Worlds in Text](https://mlsanity.com/paper/2106.09578/) (2021)
- [I love your chain mail! Making knights smile in a fantasy game world: Open-domain goal-oriented dialogue agents](https://mlsanity.com/paper/2002.02878/) (2020)
- [Mephisto: A Framework for Portable, Reproducible, and Iterative Crowdsourcing](https://mlsanity.com/paper/2301.05154/) (2023)

## Abstract (arXiv)

While language models have become more capable of producing compelling language, we find there are still gaps in maintaining consistency, especially when describing events in a dynamically changing world. We study the setting of generating narratives in an open world text adventure game, where a graph representation of the underlying game state can be used to train models that consume and output both grounded graph representations and natural language descriptions and actions. We build a large set of tasks by combining crowdsourced and simulated gameplays with a novel dataset of complex actions in order to to construct such models. We find it is possible to improve the consistency of action narration models by training on graph contexts and targets, even if graphs are not present at test time. This is shown both in automatic metrics and human evaluations. We plan to release our code, the new set of tasks, and best performing models.