Sample Efficient Paradigms for Personalized Assessment of Taskable AI Systems

Abstract

The vast diversity of internal designs of taskable black-box AI systems and their nuanced zones of safe functionality make it difficult for a layperson to use them without unintended side effects. The focus of my dissertation is to develop paradigms that would enable a user to assess and understand the limits of an AI system's safe operability. We develop a personalized AI assessment module that lets an AI system execute instruction sequences in simulators and answer queries about these executions. Our results show that such a primitive query-response capability is sufficient to efficiently derive a user-interpretable model of the system's capabilities in fully observable settings.

Cite

Text

Verma. "Sample Efficient Paradigms for Personalized Assessment of Taskable AI Systems." International Joint Conference on Artificial Intelligence, 2023. doi:10.24963/IJCAI.2023/824

Markdown

[Verma. "Sample Efficient Paradigms for Personalized Assessment of Taskable AI Systems." International Joint Conference on Artificial Intelligence, 2023.](https://mlanthology.org/ijcai/2023/verma2023ijcai-sample/) doi:10.24963/IJCAI.2023/824

BibTeX

@inproceedings{verma2023ijcai-sample,
  title     = {{Sample Efficient Paradigms for Personalized Assessment of Taskable AI Systems}},
  author    = {Verma, Pulkit},
  booktitle = {International Joint Conference on Artificial Intelligence},
  year      = {2023},
  pages     = {7099-7100},
  doi       = {10.24963/IJCAI.2023/824},
  url       = {https://mlanthology.org/ijcai/2023/verma2023ijcai-sample/}
}