Generating Hypothetical Events for Abductive Inference

TL;DR

This paper introduces a new approach for abductive reasoning using a specialized language model to generate possible future events, improving the accuracy of selecting plausible explanations for observations.

Contribution

It presents a novel multi-task model that leverages generated hypothetical events to enhance abductive inference, outperforming previous language models.

Findings

MTL model outperforms vanilla pre-trained LMs on Abductive NLI.

Generated hypothetical events aid in better abductive reasoning.

Manual evaluation confirms the usefulness of possible next events in inference.

Abstract

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.