Enhancing the Comprehensibility of Text Explanations via Unsupervised Concept Discovery

TL;DR

ECO-Concept is an unsupervised framework that automatically discovers human-understandable concepts in text explanations, improving interpretability without relying on predefined annotations.

Contribution

It introduces a novel object-centric architecture and LLM-based evaluation to enhance the comprehensibility of automatically discovered concepts in explainable AI.

Findings

Outperforms existing methods across multiple tasks

Learns more comprehensible concepts than current approaches

Enhances the interpretability of text explanations

Abstract

Concept-based explainable approaches have emerged as a promising method in explainable AI because they can interpret models in a way that aligns with human reasoning. However, their adaption in the text domain remains limited. Most existing methods rely on predefined concept annotations and cannot discover unseen concepts, while other methods that extract concepts without supervision often produce explanations that are not intuitively comprehensible to humans, potentially diminishing user trust. These methods fall short of discovering comprehensible concepts automatically. To address this issue, we propose \textbf{ECO-Concept}, an intrinsically interpretable framework to discover comprehensible concepts with no concept annotations. ECO-Concept first utilizes an object-centric architecture to extract semantic concepts automatically. Then the comprehensibility of the extracted concepts is evaluated by large language models. Finally, the evaluation result guides the subsequent model fine-tuning to obtain more understandable explanations. Experiments show that our method achieves superior performance across diverse tasks. Further concept evaluations validate that the concepts learned by ECO-Concept surpassed current counterparts in comprehensibility.