ExplaGraphs: An Explanation Graph Generation Task for Structured Commonsense Reasoning

TL;DR

ExplaGraphs introduces a new task and dataset for generating explanation graphs in commonsense reasoning, emphasizing the importance of reasoning transparency and quality over simple discriminative answers.

Contribution

The paper presents ExplaGraphs, a novel structured explanation graph generation task with a new dataset, a verification framework, and baseline models, advancing explainability in commonsense reasoning.

Findings

High-quality explanation graphs with diverse structures achieved (up to 90%)

Most graphs (79%) contain external commonsense nodes

Significant gap between model and human performance on the task

Abstract

Recent commonsense-reasoning tasks are typically discriminative in nature, where a model answers a multiple-choice question for a certain context. Discriminative tasks are limiting because they fail to adequately evaluate the model's ability to reason and explain predictions with underlying commonsense knowledge. They also allow such models to use reasoning shortcuts and not be "right for the right reasons". In this work, we present ExplaGraphs, a new generative and structured commonsense-reasoning task (and an associated dataset) of explanation graph generation for stance prediction. Specifically, given a belief and an argument, a model has to predict if the argument supports or counters the belief and also generate a commonsense-augmented graph that serves as non-trivial, complete, and unambiguous explanation for the predicted stance. We collect explanation graphs through a novel Create-Verify-And-Refine graph collection framework that improves the graph quality (up to 90%) via multiple rounds of verification and refinement. A significant 79% of our graphs contain external commonsense nodes with diverse structures and reasoning depths. Next, we propose a multi-level evaluation framework, consisting of automatic metrics and human evaluation, that check for the structural and semantic correctness of the generated graphs and their degree of match with ground-truth graphs. Finally, we present several structured, commonsense-augmented, and text generation models as strong starting points for this explanation graph generation task, and observe that there is a large gap with human performance, thereby encouraging future work for this new challenging task. ExplaGraphs will be publicly available at https://explagraphs.github.io.