Papers with bias transfer hypothesis

2 papers
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.
Bias after Prompting: Persistent Discrimination in Large Language Models (2025.findings-emnlp)

Copied to clipboard

Challenge: a dangerous assumption is that biases do not transfer from pre-trained large language models to adapted models.
Approach: They validate the bias transfer hypothesis by using prompt adaptations to study biases in causal models . they find that popular prompt-based mitigation methods do not consistently prevent biase transferring .
Outcome: The results invalidate the assumption that biases do not transfer from pre-trained models to adapted models.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations