Probing Classifiers Are Unreliable for Concept Removal and Detection

Item #:

068431-1308

Details

DOI: https://doi.org/10.52202/068431-1308
Author(s): Abhinav Kumar, Amit Sharma, Chenhao Tan
Pages: 17994-18008 (15 pages)
Format: PDF Paper Download
Conference: Advances in Neural Information Processing Systems 35
Date/Location: Held 28 November - 9 December 2022, New Orleans, Louisiana, USA.
Series: Advances in Neural Information Processing Systems 35
Publisher: Neural Information Processing Systems Foundation, Inc. (NeurIPS)

DOI: https://doi.org/10.52202/068431-1308
Author(s): Abhinav Kumar, Amit Sharma, Chenhao Tan
Pages: 17994-18008 (15 pages)
Format: PDF Paper Download
Conference: Advances in Neural Information Processing Systems 35
Date/Location: Held 28 November - 9 December 2022, New Orleans, Louisiana, USA.
Series: Advances in Neural Information Processing Systems 35
Publisher: Neural Information Processing Systems Foundation, Inc. (NeurIPS)