Reference-Based Bias Detection in LLMs via Relative Representations of Hidden States
A reference-based method that audits bias in hidden-state representations across related model variants across related model variants, for example before and after fine-tuning, which is complementary to output-based auditing rather than a replacement for it.
M. Jeliński, Jan Dubinski, Maciej Chrabaszcz et al.
· 0 citations