Papers by Michael Wick
Upstream Mitigation Is Not All You Need: Testing the Bias Transfer Hypothesis in Pre-Trained Language Models (2022.acl-long)
Copied to clipboard
| Challenge: | Large language models and other massively pre-trained "foundation" models can easily adapt to a wide variety of downstream tasks in a process called finetuning. |
| Approach: | They propose to use the bias transfer hypothesis to reduce social biases internalized by large language models during pre-training into harmful task-specific behavior after fine-tuning. |
| Outcome: | The bias transfer hypothesis is the theory that social biases internalized by large language models during pre-training transfer into harmful task-specific behavior after fine-tuning. |
Don’t Just Clean It, Proxy Clean It: Mitigating Bias by Proxy in Pre-Trained Models (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Transformer-based pre-trained models can encode societal biases in their contextual representations and in downstream predictions when fine-tuned on task-specific data. |
| Approach: | They propose an approach that selectively eliminates stereotypical associations at fine-tuning, so that the model doesn't learn to excessively rely on those signals. |
| Outcome: | The proposed approach reduces biases from identity words and frequently co-occurring proxies by > 60% in toxicity classification, and also extends to multiple identities. |