Firehose

30 JUL 2026 · Paper

Fairness Pruning: Locating Demographic Bias in GLU-MLP Layers via Differential Activations

This paper develops a technique to identify and mitigate demographic bias in large language models by selectively pruning specific neurons in neural networks, without significantly impacting the model's overall performance. Practitioners in AI and NLP may care about this method as it could help create more fair and transparent language models.

fairness bias neural pruning language models deep learning

Browse by tag

Fairness Pruning: Locating Demographic Bias in GLU-MLP Layers via Differential Activations