BERT-base-cased

text · discriminative · anchor

Findings

• IC-1544The latent spaces of pretrained foundational models across vision and text are not related by a single class of geometric transformations; the optimal alignment depends on the specific model pair, architecture, and dataset.
• IC-309As zero-shot safety judges, GPT-4o achieves 78.9% Cohen's kappa agreement with human annotators while Llama-3-8B-instruct (39.0%) and Mistral-7B-instruct-v0.2 (53.9%) perform substantially worse