Ethos: Rectifying Language Models in Orthogonal Parameter Space
Open Access
- 1 January 2024
- conference paper
- Published by Association for Computational Linguistics (ACL)
- p. 2054-2068
Abstract
Lei Gao, Yue Niu, Tingting Tang, Salman Avestimehr, Murali Annavaram. Findings of the Association for Computational Linguistics: NAACL 2024. 2024.Keywords
All Related Versions
This publication has 25 references indexed in Scilit:
- Bias and Fairness in Large Language Models: A SurveyComputational Linguistics, 2024
- All Rivers Run to the Sea: Private Learning with Asymmetric Flows2024
- Separate the Wheat from the Chaff: Model Deficiency Unlearning via Parameter-Efficient Module OperationProceedings of the AAAI Conference on Artificial Intelligence, 2024
- Membership Inference Attacks on Machine Learning: A SurveyACM Computing Surveys, 2022
- Self-Diagnosis and Self-Debiasing: A Proposal for Reducing Corpus-Based Bias in NLPTransactions of the Association for Computational Linguistics, 2021
- Data and its (dis)contents: A survey of dataset development and use in machine learning researchPatterns, 2021
- Machine Unlearning2021
- StereoSet: Measuring stereotypical bias in pretrained language models2021
- Null It Out: Guarding Protected Attributes by Iterative Nullspace Projection2020
- Nuanced Metrics for Measuring Unintended Bias with Real Data for Text Classification2019