SOURCE-LINKED INTELLIGENCE

Reference-Based Bias Detection in LLMs via Relative Representations of Hidden States

arXiv · AI, language, vision and robotics · article · Sep 9, 2026 · UTC

Existing bias auditing methods typically rely on model outputs, requiring costly benchmarks or judge models and potentially missing internal shifts that never appear in generated text. We propose a reference-based method that audits bias in hidden-state representations across related model variants, for example before and after fine-tuning. Because fine-tuning reshapes representation geometry, absolute hidden states are not directly comparable, so we encode each sentence by its similarities to a fixed set of anchor sentences, yielding relative representations in a shared comparison space. Ther

Read original source ↗ Open in workspace

recordType

paper

region

Global