Explainable AI needs formal notions of explanation correctness
Panknin D, Zhumagambetov R, Clark B, Wilming R, Haufe S, Boubekki Aexplainable AI, XAI, formalization, correctness, validation, benchmarking
| Document type | Proceedings |
| Journal title / Source | Workshop at Neural Information Processing Systems 2024 |
| Volume | 38 |
| Issue | Interpreta |
| Page numbers / Article number | article number 5 |
| Publisher's name | NA |
| Publisher's address (city only) | NA |
| Publication date | 2024-10-10 |
| Conference name | The Thirty-Eighth Annual Conference on Neural Information Processing Systems |
| Conference date | 10-12-2024 to 15-12-2024 |
| Conference place | Vancouver Convention Center |
| ISSN | NA |
| ISBN | NA |
| Language | English |
| Persistent Identifier | https://doi.org/10.48550/arXiv.2409.14590 |