Understanding Undesirable Word Embedding Associations

arXiv:1908.06361 · cs.CL · Submitted 2026-08-17 · Read on arXiv

Kawin Ethayarajh, David Duvenaud, Graeme Hirst

cs.CL

Submitted: 2026-08-17

Updated: 2026-08-19

Comments: Accepted to ACL 2019

Code: https://github.com/tolga-b/debiaswe

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Embeddings — 34× in this paper · explained in 2 episodes
• Reconstruction Error — 14× in this paper · explained in 2 episodes
• Cosine Similarity — 4× in this paper · explained in 3 episodes
• Interpretability — 2× in this paper · explained in 15 episodes
• Robustness — 2× in this paper · explained in 5 episodes
• Actor — 1× in this paper · explained in 3 episodes
• Adam — 1× in this paper · explained in 2 episodes

Sources

• Towards Understanding Linear Word Analogies
• Lipstick on a Pig: Debiasing Methods Cover up Systematic Gender Biases in Word Embeddings But do not Remove Them

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering