Does Faithfulness Conflict with Plausibility? An Empirical Study in Explainable AI across NLP Tasks

arXiv:2404.00140v1 Announce Type: cross
Abstract: Explainability algorithms aimed at interpreting decision-making AI systems usually consider balancing two critical dimensions: 1) \textit{faithfulness}, where explanations accurately reflect the model's inference process. 2) \textit{plausibility}, where explanations are consistent with domain experts. However, the question arises: do faithfulness and plausibility inherently conflict? In this study, through a comprehensive quantitative comparison between the explanations from the selected explainability methods and expert-level interpretations across three NLP tasks: sentiment analysis, intent detection, and topic labeling, we demonstrate …

abstract ai systems algorithms arxiv conflict consistent cs.ai cs.lg decision dimensions domain domain experts experts explainability explainable ai however inference making nlp process question study systems tasks type