BibTeX

@inProceedings{johansson-2024-what-337926,
	title        = {What Happens to a Dataset Transformed by a Projection-based Concept Removal Method?},
	abstract     = {We investigate the behavior of methods using linear projections to remove information about a concept from a language representation, and we consider the question of what happens to a dataset transformed by such a method. A theoretical analysis and experiments on real-world and synthetic data show that these methods inject strong statistical dependencies into the transformed datasets. After applying such a method, the representation space is highly structured: in the transformed space, an instance tends to be located near instances of the opposite label. As a consequence, the original labeling can in some cases be reconstructed by applying an anti-clustering method.},
	booktitle    = {Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 17486–17492, Torino, Italy.},
	author       = {Johansson, Richard},
	year         = {2024},
	publisher    = {ELRA and ICCL},
}