Mediators: Conversational Agents Explaining NLP Model Behavior
This addresses the problem of making AI explanations more interactive and human-centric for users in the HCXAI community, but it is incremental as it builds on existing ideas without introducing a new method.
The paper tackles the need for conversational explanations of NLP model behavior by proposing desiderata for text-based agents called Mediators, and assesses current research progress towards dialogue-based explanations for sentiment analysis.
The human-centric explainable artificial intelligence (HCXAI) community has raised the need for framing the explanation process as a conversation between human and machine. In this position paper, we establish desiderata for Mediators, text-based conversational agents which are capable of explaining the behavior of neural models interactively using natural language. From the perspective of natural language processing (NLP) research, we engineer a blueprint of such a Mediator for the task of sentiment analysis and assess how far along current research is on the path towards dialogue-based explanations.