LEACE: Perfect linear concept erasure in closed form

v1v2v3v4 (latest)

LEACE: Perfect linear concept erasure in closed form

6 June 2023

David Schneider-Joseph

Shauli Ravfogel

Stella Biderman

ArXiv (abs)PDF HTML

Papers citing "LEACE: Perfect linear concept erasure in closed form"

19 / 119 papers shown

Title
Obstructing Classification via Projection P. Haghighatkhah Wouter Meulemans Bettina Speckmann Jérôme Urhausen Kevin Verbeek 45 6 0 19 May 2021
The Low-Dimensional Linear Geometry of Contextualized Word Representations Evan Hernandez Jacob Andreas MILM 96 45 0 15 May 2021
Counterfactual Interventions Reveal the Causal Effect of Relative Clause Representations on Agreement Prediction Shauli Ravfogel Grusha Prasad Tal Linzen Yoav Goldberg 72 59 0 14 May 2021
The Rediscovery Hypothesis: Language Models Need to Meet Linguistics Vassilina Nikoulina Maxat Tezekbayev Nuradil Kozhakhmet Madina Babazhanova Matthias Gallé Z. Assylbekov 52 8 0 02 Mar 2021
The Pile: An 800GB Dataset of Diverse Text for Language Modeling Leo Gao Stella Biderman Sid Black Laurence Golding Travis Hoppe ... Horace He Anish Thite Noa Nabeshima Shawn Presser Connor Leahy AIMat 466 2,120 0 31 Dec 2020
OSCaR: Orthogonal Subspace Correction and Rectification of Biases in Word Embeddings Sunipa Dev Tao Li J. M. Phillips Vivek Srikumar 68 55 0 30 Jun 2020
Universal Dependencies v2: An Evergrowing Multilingual Treebank Collection Joakim Nivre M. Marneffe Filip Ginter Jan Hajivc Christopher D. Manning S. Pyysalo Sebastian Schuster Francis M. Tyers Daniel Zeman VLM 54 516 0 22 Apr 2020
Null It Out: Guarding Protected Attributes by Iterative Nullspace Projection Shauli Ravfogel Yanai Elazar Hila Gonen Michael Twiton Yoav Goldberg 138 388 0 16 Apr 2020
A Theory of Usable Information Under Computational Constraints Yilun Xu Shengjia Zhao Jiaming Song Russell Stewart Stefano Ermon 79 175 0 25 Feb 2020
On the Global Optima of Kernelized Adversarial Representation Learning Bashir Sadeghi Runyi Yu Vishnu Boddeti AAML 81 31 0 16 Oct 2019
BERT Rediscovers the Classical NLP Pipeline Ian Tenney Dipanjan Das Ellie Pavlick MILM SSeg 138 1,478 0 15 May 2019
Bias in Bios: A Case Study of Semantic Representation Bias in a High-Stakes Setting Maria De-Arteaga Alexey Romanov Hanna M. Wallach J. Chayes C. Borgs Alexandra Chouldechova S. Geyik K. Kenthapadi Adam Tauman Kalai 194 460 0 27 Jan 2019
Adversarial Removal of Demographic Attributes from Text Data Yanai Elazar Yoav Goldberg FaML 109 309 0 20 Aug 2018
Mitigating Unwanted Biases with Adversarial Learning B. Zhang Blake Lemoine Margaret Mitchell FaML 199 1,390 0 22 Jan 2018
Controllable Invariance through Adversarial Feature Learning Qizhe Xie Zihang Dai Yulun Du Eduard H. Hovy Graham Neubig OOD 94 293 0 31 May 2017
Counterfactual Fairness Matt J. Kusner Joshua R. Loftus Chris Russell Ricardo M. A. Silva FaML 224 1,586 0 20 Mar 2017
Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings Tolga Bolukbasi Kai-Wei Chang James Zou Venkatesh Saligrama Adam Kalai CVBM FaML 112 3,150 0 21 Jul 2016
Adversarial Deep Averaging Networks for Cross-Lingual Sentiment Classification Xilun Chen Yu Sun Ben Athiwaratkun Claire Cardie Kilian Q. Weinberger 267 316 0 06 Jun 2016
Censoring Representations with an Adversary Harrison Edwards Amos Storkey AAML FaML 66 506 0 18 Nov 2015