# Reasoning about Actions and State Changes by Injecting Commonsense Knowledge

arXiv: https://arxiv.org/abs/1808.10012 · HTML: https://mlsanity.com/paper/1808.10012/

## Key facts

- Cited by 29 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Aug 2018.

## Built on by (most cited first, 29 of 29)

- [Natural Language Reasoning, A Survey](https://mlsanity.com/paper/2303.14725/) (2023)
- [General-Purpose Question-Answering with Macaw](https://mlsanity.com/paper/2109.02593/) (2021)
- [DISCOS: Bridging the Gap between Discourse Knowledge and Commonsense Knowledge](https://mlsanity.com/paper/2101.00154/) (2021)
- [SCHEMA: State CHangEs MAtter for Procedure Planning in Instructional Videos](https://mlsanity.com/paper/2403.01599/) (2024)
- [Time-Stamped Language Model: Teaching Language Models to Understand the Flow of Events](https://mlsanity.com/paper/2104.07635/) (2021)
- [Life is a Circus and We are the Clowns: Automatically Finding Analogies between Situations and Processes](https://mlsanity.com/paper/2210.12197/) (2022)
- [Think about it! Improving defeasible reasoning by first modeling the question scenario](https://mlsanity.com/paper/2110.12349/) (2021)
- [A Systematic Survey of Text Worlds as Embodied Natural Language Environments](https://mlsanity.com/paper/2107.04132/) (2021)
- [MARS: Benchmarking the Metaphysical Reasoning Abilities of Language Models with a Multi-task Evaluation Dataset](https://mlsanity.com/paper/2406.02106/) (2024)
- [Coalescing Global and Local Information for Procedural Text Understanding](https://mlsanity.com/paper/2208.12848/) (2022)
- [Elaboration-Generating Commonsense Question Answering at Scale](https://mlsanity.com/paper/2209.01232/) (2022)
- [What Makes the Story Forward? Inferring Commonsense Explanations as Prompts for Future Event Generation](https://mlsanity.com/paper/2201.07099/) (2022)
- [EvEntS ReaLM: Event Reasoning of Entity States via Language Models](https://mlsanity.com/paper/2211.05392/) (2022)
- [LEMON: Language-Based Environment Manipulation via Execution-Guided Pre-training](https://mlsanity.com/paper/2201.08081/) (2022)
- [Enriching a Model's Notion of Belief using a Persistent Memory](https://mlsanity.com/paper/2104.08401/) (2021)
- [Relational Gating for "What If" Reasoning](https://mlsanity.com/paper/2105.13449/) (2021)
- [Learning Action Conditions from Instructional Manuals for Instruction Understanding](https://mlsanity.com/paper/2205.12420/) (2022)
- [The Role of Semantic Parsing in Understanding Procedural Text](https://mlsanity.com/paper/2302.06829/) (2023)
- [Tracking entities in technical procedures -- a new dataset and baselines](https://mlsanity.com/paper/2104.07378/) (2021)
- [50 Ways to Bake a Cookie: Mapping the Landscape of Procedural Texts](https://mlsanity.com/paper/2210.17235/) (2022)
- [Template Filling for Controllable Commonsense Reasoning](https://mlsanity.com/paper/2111.00539/) (2021)
- [Procedural Text Understanding via Scene-Wise Evolution](https://mlsanity.com/paper/2203.07600/) (2022)
- [Entity Tracking via Effective Use of Multi-Task Learning Model and Mention-guided Decoding](https://mlsanity.com/paper/2210.06444/) (2022)
- [Understanding in Artificial Intelligence](https://mlsanity.com/paper/2101.06573/) (2021)
- [FABLE: A Novel Data-Flow Analysis Benchmark on Procedural Text for Large Language Model Evaluation](https://mlsanity.com/paper/2505.24258/) (2025)
- [When LLMs Stop Following Steps: A Diagnostic Study of Procedural Execution in Language Models](https://mlsanity.com/paper/2605.00817/) (2026)
- [Teaching Through Analogies: A Modular Pipeline for Educational Analogy Generation](https://mlsanity.com/paper/2605.24211/) (2026)
- [YeasierAgent: Agentic Social Sandbox as a Canvas for Intent-Driven Creation of Platform-Agnostic Symbiotic Agent-Native Applications](https://mlsanity.com/paper/2606.13722/) (2026)
- [PACE: Precise AI Cinematic Expression](https://mlsanity.com/paper/2609.19853/) (2026)

## Abstract (arXiv)

Comprehending procedural text, e.g., a paragraph describing photosynthesis, requires modeling actions and the state changes they produce, so that questions about entities at different timepoints can be answered. Although several recent systems have shown impressive progress in this task, their predictions can be globally inconsistent or highly improbable. In this paper, we show how the predicted effects of actions in the context of a paragraph can be improved in two ways: (1) by incorporating global, commonsense constraints (e.g., a non-existent entity cannot be destroyed), and (2) by biasing reading with preferences from large-scale corpora (e.g., trees rarely move). Unlike earlier methods, we treat the problem as a neural structured prediction task, allowing hard and soft constraints to steer the model away from unlikely predictions. We show that the new model significantly outperforms earlier systems on a benchmark dataset for procedural text comprehension (+8% relative gain), and that it also avoids some of the nonsensical predictions that earlier systems make.