Towards an Explainer-Agnostic Conversational XAI

Abstract

Explainable Artificial Intelligence (XAI) is gaining interests in both academia and industry, mainly thanks to the proliferation of darker more complex black-box solutions which are replacing their more transparent ancestors. Believing that the overall performance of an XAI system can be augmented by considering the end-user as a human being, we are studying the ways we can improve the explanations by making them more informative and easier to use from one hand, and interactive and customisable from the other hand.

Cite

Text

Nobani et al. "Towards an Explainer-Agnostic Conversational XAI." International Joint Conference on Artificial Intelligence, 2021. doi:10.24963/IJCAI.2021/686

Markdown

[Nobani et al. "Towards an Explainer-Agnostic Conversational XAI." International Joint Conference on Artificial Intelligence, 2021.](https://mlanthology.org/ijcai/2021/nobani2021ijcai-explainer/) doi:10.24963/IJCAI.2021/686

BibTeX

@inproceedings{nobani2021ijcai-explainer,
  title     = {{Towards an Explainer-Agnostic Conversational XAI}},
  author    = {Nobani, Navid and Mercorio, Fabio and Mezzanzanica, Mario},
  booktitle = {International Joint Conference on Artificial Intelligence},
  year      = {2021},
  pages     = {4909-4910},
  doi       = {10.24963/IJCAI.2021/686},
  url       = {https://mlanthology.org/ijcai/2021/nobani2021ijcai-explainer/}
}