Work

Mediators: Conversational Agents Explaining NLP Model Behavior

Year: 2022

Type: preprint

Abstract: 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.

Source: arXiv (Cornell University)

DOI: 10.48550/arxiv.2206.06029

Authors: Feldhus, Nils, Ravichandran, Ajay Madhavan, Möller, Sebastian

Institutions: German Research Centre for Artificial Intelligence, Technische Universität Berlin

Language: English

Topic: Explainable Artificial Intelligence (XAI)

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

Funder: Bundesministerium für Bildung und Forschung

Award: G6422402235

OpenAlex ID: W4320202382

Cites:

Cited by: 10

Related to: 10