@inproceedings{Leofante:2023:10.1007/978-3-031-43264-4_16,
author = {Leofante, F and Lomuscio, A},
doi = {10.1007/978-3-031-43264-4_16},
pages = {244--262},
publisher = {Springer},
title = {Robust explanations for human-neural multi-agent systems with formal verification},
url = {http://dx.doi.org/10.1007/978-3-031-43264-4_16},
year = {2023}
}

Download

TY  - CPAPER
AB  - The quality of explanations in human-agent interactions isfundamental to the development of trustworthy AI systems. In this paper we study the problem of generating robust contrastive explanations for human-neural multi-agent systems and introduce two novel verification-based algorithms to (i) identify non-robust explanations generated by other methods and (ii) generate contrastive explanations equipped with formal robustness certificates. We present an implementation and evaluate the effectiveness of the approach on two case studies involving neural agents trained on credit scoring and traffic sign recognition tasks.
AU  - Leofante,F
AU  - Lomuscio,A
DO  - 10.1007/978-3-031-43264-4_16
EP  - 262
PB  - Springer
PY  - 2023///
SN  - 1611-3349
SP  - 244
TI  - Robust explanations for human-neural multi-agent systems with formal verification
UR  - http://dx.doi.org/10.1007/978-3-031-43264-4_16
UR  - https://link.springer.com/chapter/10.1007/978-3-031-43264-4_16
UR  - http://hdl.handle.net/10044/1/106148
ER  - 

Download