Web: http://arxiv.org/abs/2205.01366

May 4, 2022, 1:11 a.m. | Jeevesh Juneja, Ritu Agarwal

cs.LG updates on arXiv.org arxiv.org

We analyze the Knowledge Neurons framework for the attribution of factual and
relational knowledge to particular neurons in the transformer network. We use a
12-layer multi-lingual BERT model for our experiments. Our study reveals
various interesting phenomena. We observe that mostly factual knowledge can be
attributed to middle and higher layers of the network($\ge 6$). Further
analysis reveals that the middle layers($6-9$) are mostly responsible for
relational information, which is further refined into actual factual knowledge
or the "correct answer" …

arxiv attribution knowledge patterns transformers

More from arxiv.org / cs.LG updates on arXiv.org

Data Analyst, Patagonia Action Works

@ Patagonia | Remote

Data & Insights Strategy & Innovation General Manager

@ Chevron Services Company, a division of Chevron U.S.A Inc. | Houston, TX

Faculty members in Research areas such as Bayesian and Spatial Statistics; Data Privacy and Security; AI/ML; NLP; Image and Video Data Analysis

@ Ahmedabad University | Ahmedabad, India

Director, Applied Mathematics & Computational Research Division

@ Lawrence Berkeley National Lab | Berkeley, Ca

Business Data Analyst

@ MainStreet Family Care | Birmingham, AL

Assistant/Associate Professor of the Practice in Business Analytics

@ Georgetown University McDonough School of Business | Washington DC