# Relevant CommonSense Subgraphs for "What if..." Procedural Reasoning

arXiv: https://arxiv.org/abs/2203.11187 · HTML: https://mlsanity.com/paper/2203.11187/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Knowledge- and tool-augmented reasoning, one of 17 directions in LLM reasoning.
- Builds on 17 of its 21 references that are in the map.
- First posted on arXiv 21 Mar 2022.

## Placed in

- LLM reasoning / [Knowledge- and tool-augmented reasoning](https://mlsanity.com/lr/knowledge-and-tool-augmented-reasoning/)

## Builds on (most cited first, 17 of 17)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledge](https://mlsanity.com/paper/1811.00937/) (2018)
- [Modeling Relational Data with Graph Convolutional Networks](https://mlsanity.com/paper/1703.06103/) (2017)
- [ConceptNet 5.5: An Open Multilingual Graph of General Knowledge](https://mlsanity.com/paper/1612.03975/) (2016)
- [Bidirectional Attention Flow for Machine Comprehension](https://mlsanity.com/paper/1611.01603/) (2016)
- [KagNet: Knowledge-Aware Graph Networks for Commonsense Reasoning](https://mlsanity.com/paper/1909.02151/) (2019)
- [A Decomposable Attention Model for Natural Language Inference](https://mlsanity.com/paper/1606.01933/) (2016)
- [Logic-Guided Data Augmentation and Regularization for Consistent Question Answering](https://mlsanity.com/paper/2004.10157/) (2020)
- [WIQA: A dataset for "What if..." reasoning over procedural text](https://mlsanity.com/paper/1909.04739/) (2019)
- [Graph-Based Reasoning over Heterogeneous External Knowledge for Commonsense Question Answering](https://mlsanity.com/paper/1909.05311/) (2019)
- [Cross-Modality Relevance for Reasoning on Language and Vision](https://mlsanity.com/paper/2005.06035/) (2020)
- [What-if I ask you to explain: Explaining the effects of perturbations in procedural text](https://mlsanity.com/paper/2005.01526/) (2020)
- [EIGEN: Event Influence GENeration using Pre-trained Language Models](https://mlsanity.com/paper/2010.11764/) (2020)
- [REM-Net: Recursive Erasure Memory Network for Commonsense Evidence Refinement](https://mlsanity.com/paper/2012.13185/) (2020)
- [Relational Gating for "What If" Reasoning](https://mlsanity.com/paper/2105.13449/) (2021)

## Built on by (most cited first, 2 of 2)

- [GLUECons: A Generic Benchmark for Learning Under Constraints](https://mlsanity.com/paper/2302.10914/) (2023)
- [Dynamic Relevance Graph Network for Knowledge-Aware Question Answering](https://mlsanity.com/paper/2209.09947/) (2022)

## Abstract (arXiv)

We study the challenge of learning causal reasoning over procedural text to answer "What if..." questions when external commonsense knowledge is required. We propose a novel multi-hop graph reasoning model to 1) efficiently extract a commonsense subgraph with the most relevant information from a large knowledge graph; 2) predict the causal answer by reasoning over the representations obtained from the commonsense subgraph and the contextual interactions between the questions and context. We evaluate our model on WIQA benchmark and achieve state-of-the-art performance compared to the recent models.