all AI news
Decoding Probing: Revealing Internal Linguistic Structures in Neural Language Models using Minimal Pairs
March 27, 2024, 4:48 a.m. | Linyang He, Peili Chen, Ercong Nie, Yuanning Li, Jonathan R. Brennan
cs.CL updates on arXiv.org arxiv.org
Abstract: Inspired by cognitive neuroscience studies, we introduce a novel `decoding probing' method that uses minimal pairs benchmark (BLiMP) to probe internal linguistic characteristics in neural language models layer by layer. By treating the language model as the `brain' and its representations as `neural activations', we decode grammaticality labels of minimal pairs from the intermediate layers' representations. This approach reveals: 1) Self-supervised language models capture abstract linguistic structures in intermediate layers that GloVe and RNN language …
abstract arxiv benchmark brain cognitive cs.cl decoding language language model language models layer neuroscience novel probe q-bio.nc studies type
More from arxiv.org / cs.CL updates on arXiv.org
Jobs in AI, ML, Big Data
Data Architect
@ University of Texas at Austin | Austin, TX
Data ETL Engineer
@ University of Texas at Austin | Austin, TX
Lead GNSS Data Scientist
@ Lurra Systems | Melbourne
Senior Machine Learning Engineer (MLOps)
@ Promaton | Remote, Europe
Reporting & Data Analytics Lead (Sizewell C)
@ EDF | London, GB
Data Analyst
@ Notable | San Mateo, CA