Linear Probing
Linear probing is a technique used to analyze and understand the internal representations of complex machine learning models, primarily focusing on identifying what information the model has learned and how it's encoded. Current research explores linear probing's application in diverse areas, including assessing copyright infringement in large language models, improving transfer learning via enhanced probing layers (e.g., Kolmogorov-Arnold Networks), and detecting adversarial examples and biases. This methodology offers valuable insights into model interpretability, facilitating the development of more robust, reliable, and ethically sound AI systems across various domains, from natural language processing to medical image analysis.
Papers
June 19, 2024
May 30, 2024
May 27, 2024
April 10, 2024
April 2, 2024
March 26, 2024
February 29, 2024
February 22, 2024
February 8, 2024
February 4, 2024
January 22, 2024
December 21, 2023
December 15, 2023
December 8, 2023
December 7, 2023
November 30, 2023
November 25, 2023
November 7, 2023
November 1, 2023