Talking Back -- human input and explanations to interactive AI systems

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.

@article{dix2025_2503.04343,
  title={ Talking Back -- human input and explanations to interactive AI systems },
  author={ Alan Dix and Tommaso Turchi and Ben Wilson and Anna Monreale and Matt Roach },
  journal={arXiv preprint arXiv:2503.04343},
  year={ 2025 }
}