all AI news
Effective Controllable Bias Mitigation for Classification and Retrieval using Gate Adapters. (arXiv:2401.16457v1 [cs.LG])
cs.LG updates on arXiv.org arxiv.org
Bias mitigation of Language Models has been the topic of many studies with a
recent focus on learning separate modules like adapters for on-demand
debiasing. Besides optimizing for a modularized debiased model, it is often
critical in practice to control the degree of bias reduction at inference time,
e.g., in order to tune for a desired performance-fairness trade-off in search
results or to control the strength of debiasing in classification tasks. In
this paper, we introduce Controllable Gate Adapter (ConGater), …
arxiv bias classification control cs.lg demand focus gate inference language language models modules practice retrieval studies