New Framework Proposes Task-Agnostic Counterfactual Fairness for Transformers via Activation Steering
A new arXiv paper introduces a framework aimed at reducing bias in transformer-based models through activation steering, targeting counterfactual fairness in automated decision-making systems.
Read the full story at arXiv cs.LG ↗
Timeline · 1 report
- 2026-11-03 05:00 · arXiv cs.LG
A Framework for Task-Agnostic Counterfactual Fairness in Transformers through Activation Steering