# Generating Hypothetical Events for Abductive Inference

arXiv: https://arxiv.org/abs/2106.03973 · HTML: https://mlsanity.com/paper/2106.03973/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 50 references that are in the map.
- First posted on arXiv 7 Jun 2021.

## Builds on (most cited first, 27 of 27)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledge](https://mlsanity.com/paper/1811.00937/) (2018)
- [ConceptNet 5.5: An Open Multilingual Graph of General Knowledge](https://mlsanity.com/paper/1612.03975/) (2016)
- [Annotation Artifacts in Natural Language Inference Data](https://mlsanity.com/paper/1803.02324/) (2018)
- [e-SNLI: Natural Language Inference with Natural Language Explanations](https://mlsanity.com/paper/1812.01193/) (2018)
- [Supervised Learning of Universal Sentence Representations from Natural Language Inference Data](https://mlsanity.com/paper/1705.02364/) (2017)
- [A Corpus and Evaluation Framework for Deeper Understanding of Commonsense Stories](https://mlsanity.com/paper/1604.01696/) (2016)
- [Explain Yourself! Leveraging Language Models for Commonsense Reasoning](https://mlsanity.com/paper/1906.02361/) (2019)
- [Abductive Commonsense Reasoning](https://mlsanity.com/paper/1908.05739/) (2019)
- [Cosmos QA: Machine Reading Comprehension with Contextual Commonsense Reasoning](https://mlsanity.com/paper/1909.00277/) (2019)
- [KagNet: Knowledge-Aware Graph Networks for Commonsense Reasoning](https://mlsanity.com/paper/1909.02151/) (2019)
- [Enhanced LSTM for Natural Language Inference](https://mlsanity.com/paper/1609.06038/) (2016)
- [Multimodal Explanations: Justifying Decisions and Pointing to the Evidence](https://mlsanity.com/paper/1802.08129/) (2018)
- [Generating Fact Checking Explanations](https://mlsanity.com/paper/2004.05773/) (2020)
- [Compositional Questions Do Not Necessitate Multi-hop Reasoning](https://mlsanity.com/paper/1906.02900/) (2019)
- [Counterfactual Story Reasoning and Generation](https://mlsanity.com/paper/1909.04076/) (2019)
- [Event2Mind: Commonsense Inference on Events, Intents, and Reactions](https://mlsanity.com/paper/1805.06939/) (2018)
- [WIQA: A dataset for "What if..." reasoning over procedural text](https://mlsanity.com/paper/1909.04739/) (2019)
- [Language Generation with Multi-Hop Reasoning on Commonsense Knowledge Graph](https://mlsanity.com/paper/2009.11692/) (2020)
- [When Choosing Plausible Alternatives, Clever Hans can be Clever](https://mlsanity.com/paper/1911.00225/) (2019)
- [Explaining Question Answering Models through Text Generation](https://mlsanity.com/paper/2004.05569/) (2020)
- [A Survey on Explainability in Machine Reading Comprehension](https://mlsanity.com/paper/2010.00389/) (2020)
- [Ranking and Selecting Multi-Hop Knowledge Paths to Better Predict Human Needs](https://mlsanity.com/paper/1904.00676/) (2019)
- [COINS: Dynamically Generating COntextualized Inference Rules for Narrative Story Completion](https://mlsanity.com/paper/2106.02497/) (2021)
- [Social Commonsense Reasoning with Multi-Head Knowledge Attention](https://mlsanity.com/paper/2010.05587/) (2020)
- [L2R2: Leveraging Ranking for Abductive Reasoning](https://mlsanity.com/paper/2005.11223/) (2020)

## Built on by (most cited first, 3 of 3)

- [The Abduction of Sherlock Holmes: A Dataset for Visual Abductive Reasoning](https://mlsanity.com/paper/2202.04800/) (2022)
- [Black Swan: Abductive and Defeasible Video Reasoning in Unpredictable Events](https://mlsanity.com/paper/2412.05725/) (2024)
- [Exploring the Potential of Multi-Modal AI for Driving Hazard Prediction](https://mlsanity.com/paper/2310.04671/) (2023)

## Abstract (arXiv)

Abductive reasoning starts from some observations and aims at finding the most plausible explanation for these observations. To perform abduction, humans often make use of temporal and causal inferences, and knowledge about how some hypothetical situation can result in different outcomes. This work offers the first study of how such knowledge impacts the Abductive NLI task -- which consists in choosing the more likely explanation for given observations. We train a specialized language model LMI that is tasked to generate what could happen next from a hypothetical scenario that evolves from a given event. We then propose a multi-task model MTL to solve the Abductive NLI task, which predicts a plausible explanation by a) considering different possible events emerging from candidate hypotheses -- events generated by LMI -- and b) selecting the one that is most similar to the observed outcome. We show that our MTL model improves over prior vanilla pre-trained LMs fine-tuned on Abductive NLI. Our manual evaluation and analysis suggest that learning about possible next events from different hypothetical scenarios supports abductive inference.