Data Efficient Paradigms for Personalized Assessment of Black-Box 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. My dissertation focuses on developing paradigms that 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 interface is sufficient to efficiently derive a user-interpretable model of a system's capabilities.
Cite
Text
Verma. "Data Efficient Paradigms for Personalized Assessment of Black-Box Taskable AI Systems." AAAI Conference on Artificial Intelligence, 2024. doi:10.1609/AAAI.V38I21.30414Markdown
[Verma. "Data Efficient Paradigms for Personalized Assessment of Black-Box Taskable AI Systems." AAAI Conference on Artificial Intelligence, 2024.](https://mlanthology.org/aaai/2024/verma2024aaai-data/) doi:10.1609/AAAI.V38I21.30414BibTeX
@inproceedings{verma2024aaai-data,
title = {{Data Efficient Paradigms for Personalized Assessment of Black-Box Taskable AI Systems}},
author = {Verma, Pulkit},
booktitle = {AAAI Conference on Artificial Intelligence},
year = {2024},
pages = {23427-23428},
doi = {10.1609/AAAI.V38I21.30414},
url = {https://mlanthology.org/aaai/2024/verma2024aaai-data/}
}