Talking Back -- human input and explanations to interactive AI systems
This addresses the need for more interactive and collaborative AI systems, though it appears incremental by reversing the typical XAI focus.
The paper tackles the problem of enhancing human-AI synergy by exploring how human explanations can guide AI systems, resulting in more aligned automated judgments and explanations.
While XAI focuses on providing AI explanations to humans, can the reverse - humans explaining their judgments to AI - foster richer, synergistic human-AI systems? This paper explores various forms of human inputs to AI and examines how human explanations can guide machine learning models toward automated judgments and explanations that align more closely with human concepts.