all AI news
A Comparative Study of Faithfulness Metrics for Model Interpretability Methods. (arXiv:2204.05514v1 [cs.CL])
April 13, 2022, 1:11 a.m. | Chun Sik Chan, Huanqi Kong, Guanqing Liang
cs.LG updates on arXiv.org arxiv.org
Interpretation methods to reveal the internal reasoning processes behind
machine learning models have attracted increasing attention in recent years. To
quantify the extent to which the identified interpretations truly reflect the
intrinsic decision-making mechanisms, various faithfulness evaluation metrics
have been proposed. However, we find that different faithfulness metrics show
conflicting preferences when comparing different interpretations. Motivated by
this observation, we aim to conduct a comprehensive and comparative study of
the widely adopted faithfulness metrics. In particular, we introduce two
assessment …
More from arxiv.org / cs.LG updates on arXiv.org
Jobs in AI, ML, Big Data
Lead Developer (AI)
@ Cere Network | San Francisco, US
Research Engineer
@ Allora Labs | Remote
Ecosystem Manager
@ Allora Labs | Remote
Founding AI Engineer, Agents
@ Occam AI | New York
AI Engineer Intern, Agents
@ Occam AI | US
AI Research Scientist
@ Vara | Berlin, Germany and Remote