We propose Rashomon Alignment (RA), a new measure to assess functional similarity between two models. Existing functional similarity measures are distributional, quantifying differences between outputs of models applied to real-world data.
Summary generated by The Flow from the publisher's feed. The full article lives at Hugging Face Trending Papers.
arXiv:2607. 25680v1 Announce Type: cross Abstract: We propose Rashomon Alignment (RA), a new measure to assess functional similarity between two models.
arXiv:2608. 15402v1 Announce Type: new Abstract: Generative model alignment has received broad interest, and significant progress has been made in supervised fine-tuning and inference-time computation.
arXiv:2505. 20142v2 Announce Type: replace Abstract: In deep learning, functional similarity evaluation quantifies the extent to which independently trained models learn similar input--output relationships.
arXiv:2607. 29008v1 Announce Type: cross Abstract: Modern opaque AI models prize performance over interpretability, which makes testing difficult.
arXiv:2605. 24782v2 Announce Type: replace Abstract: While Vision Foundation Models (VFMs) excel at predictive tasks on satellite imagery, their performance can arise from visual correlations rather than underlying structural invariants, making even perception-based out-of-distribution accuracy a poor proxy for scientific utility.
arXiv:2602. 06205v2 Announce Type: replace-cross Abstract: The Platonic Representation Hypothesis suggests that independently trained neural networks converge to increasingly similar latent spaces.