← Search

Yusuke Takase

2 accepted papers

2025

Mapping 1,000+ Language Models via the Log-Likelihood Vector

ACL 2025long

To compare autoregressive language models at scale, we propose using log-likelihood vectors computed on a predefined text set as model features. This approach has a solid theoretical basis: when treated as model coordinates, their squared Euclidean distance approximates the Kullback-Leibler divergen…

Cited by 0SourcePDFScholar
2024

Axis Tour: Word Tour Determines the Order of Axes in ICA-transformed Embeddings

EMNLP 2024finding

Word embedding is one of the most important components in natural language processing, but interpreting high-dimensional embeddings remains a challenging problem. To address this problem, Independent Component Analysis (ICA) is identified as an effective solution. ICA-transformed word embeddings rev…