# ROCK: Causal Inference Principles for Reasoning about Commonsense Causality

arXiv: https://arxiv.org/abs/2202.00436 · HTML: https://mlsanity.com/paper/2202.00436/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- Placed in Causal reasoning in LLMs, one of 17 directions in LLM reasoning.
- Builds on 21 of its 65 references that are in the map.
- First posted on arXiv 31 Jan 2022.

## Placed in

- LLM reasoning / [Causal reasoning in LLMs](https://mlsanity.com/lr/causal-reasoning-in-llms/)

## Builds on (most cited first, 21 of 21)

- [Finetuned Language Models Are Zero-Shot Learners](https://mlsanity.com/paper/2109.01652/) (2021)
- [The Pile: An 800GB Dataset of Diverse Text for Language Modeling](https://mlsanity.com/paper/2101.00027/) (2020)
- [COMET: Commonsense Transformers for Automatic Knowledge Graph Construction](https://mlsanity.com/paper/1906.05317/) (2019)
- [AllenNLP: A Deep Semantic Natural Language Processing Platform](https://mlsanity.com/paper/1803.07640/) (2018)
- [Polyjuice: Generating Counterfactuals for Explaining, Evaluating, and Improving Models](https://mlsanity.com/paper/2101.00288/) (2021)
- [Causal Inference in Natural Language Processing: Estimation, Prediction, Interpretation and Beyond](https://mlsanity.com/paper/2109.00725/) (2021)
- [Unsupervised Commonsense Question Answering with Self-Talk](https://mlsanity.com/paper/2004.05483/) (2020)
- [GLUCOSE: GeneraLized and COntextualized Story Explanations](https://mlsanity.com/paper/2009.07758/) (2020)
- [Event2Mind: Commonsense Inference on Events, Intents, and Reactions](https://mlsanity.com/paper/1805.06939/) (2018)
- [Joint Reasoning for Temporal and Causal Relations](https://mlsanity.com/paper/1906.04941/) (2019)
- [Text and Causal Inference: A Review of Using Text to Remove Confounding from Causal Estimates](https://mlsanity.com/paper/2005.00649/) (2020)
- [When Choosing Plausible Alternatives, Clever Hans can be Clever](https://mlsanity.com/paper/1911.00225/) (2019)
- [Temporal Common Sense Acquisition with Minimal Supervision](https://mlsanity.com/paper/2005.04304/) (2020)
- [Pre-training Is (Almost) All You Need: An Application to Commonsense Reasoning](https://mlsanity.com/paper/2004.14074/) (2020)
- [An Improved Neural Baseline for Temporal Relation Extraction](https://mlsanity.com/paper/1909.00429/) (2019)
- [A Structured Learning Approach to Temporal Relation Extraction](https://mlsanity.com/paper/1906.04943/) (2019)
- [Improving Temporal Relation Extraction with a Globally Acquired Statistical Resource](https://mlsanity.com/paper/1804.06020/) (2018)
- [Incidental Supervision: Moving beyond Supervised Learning](https://mlsanity.com/paper/2005.12339/) (2020)
- [Improving Commonsense Causal Reasoning by Adversarial Training and Data Augmentation](https://mlsanity.com/paper/2101.04966/) (2021)
- [Doing Good or Doing Right? Exploring the Weakness of Commonsense Causal Reasoning Models](https://mlsanity.com/paper/2107.01791/) (2021)
- [Detecting and Explaining Causes From Text For a Time Series Event](https://mlsanity.com/paper/1707.08852/) (2017)

## Built on by (most cited first, 16 of 16)

- [Large Language Models Are Not Strong Abstract Reasoners](https://mlsanity.com/paper/2305.19555/) (2023)
- [Large Language Models and Causal Inference in Collaboration: A Survey](https://mlsanity.com/paper/2403.09606/) (2024)
- [Knowledge-in-Context: Towards Knowledgeable Semi-Parametric Language Models](https://mlsanity.com/paper/2210.16433/) (2022)
- [COLA: Contextualized Commonsense Causal Reasoning from the Causal Inference Perspective](https://mlsanity.com/paper/2305.05191/) (2023)
- [Complex Query Answering on Eventuality Knowledge Graph with Implicit Logical Constraints](https://mlsanity.com/paper/2305.19068/) (2023)
- [A Causal Explainable Guardrails for Large Language Models](https://mlsanity.com/paper/2405.04160/) (2024)
- [Event Causality Is Key to Computational Story Understanding](https://mlsanity.com/paper/2311.09648/) (2023)
- [An Overview Of Temporal Commonsense Reasoning and Acquisition](https://mlsanity.com/paper/2308.00002/) (2023)
- [Counterfactual Causal Inference in Natural Language with Large Language Models](https://mlsanity.com/paper/2410.06392/) (2024)
- [The Odyssey of Commonsense Causality: From Foundational Benchmarks to Cutting-Edge Reasoning](https://mlsanity.com/paper/2406.19307/) (2024)
- [CASA: Causality-driven Argument Sufficiency Assessment](https://mlsanity.com/paper/2401.05249/) (2024)
- [TILFA: A Unified Framework for Text, Image, and Layout Fusion in Argument Mining](https://mlsanity.com/paper/2310.05210/) (2023)
- [Some Reflections on Drawing Causal Inference using Textual Data: Parallels Between Human Subjects and Organized Texts](https://mlsanity.com/paper/2202.00848/) (2022)
- [NECE: Narrative Event Chain Extraction Toolkit](https://mlsanity.com/paper/2208.08063/) (2022)
- [Event Causality Identification with Synthetic Control](https://mlsanity.com/paper/2509.18156/) (2025)
- [Are All Steps Equally Important? Benchmarking Essentiality Detection of Events](https://mlsanity.com/paper/2210.04074/) (2022)

## Abstract (arXiv)

Commonsense causality reasoning (CCR) aims at identifying plausible causes and effects in natural language descriptions that are deemed reasonable by an average person. Although being of great academic and practical interest, this problem is still shadowed by the lack of a well-posed theoretical framework; existing work usually relies on deep language models wholeheartedly, and is potentially susceptible to confounding co-occurrences. Motivated by classical causal principles, we articulate the central question of CCR and draw parallels between human subjects in observational studies and natural languages to adopt CCR to the potential-outcomes framework, which is the first such attempt for commonsense tasks. We propose a novel framework, ROCK, to Reason O(A)bout Commonsense K(C)ausality, which utilizes temporal signals as incidental supervision, and balances confounding effects using temporal propensities that are analogous to propensity scores. The ROCK implementation is modular and zero-shot, and demonstrates good CCR capabilities.