Publications

Linear Script Representations in Speech Foundation Models Enable Zero-Shot Transliteration

Ryan Soh-Eun Shim, Kwanghee Choi, Kalvin Chang, Ming-Hao Hsu, Florian Eichin, Zhizheng Wu, Alane Suhr, Michael A. Hedderich, David Harwath, David R. Mortensen, Barbara Plank. 2026. Linear Script Representations in Speech Foundation Models Enable Zero-Shot Transliteration. arXiv:2601.02906.

We show that script is largely represented as a single linear direction in activation space of Whisper models and that steering activations towards that direction enables transcriptions and even generalizes across different languages.

Florian Eichin

Publications

Linear Script Representations in Speech Foundation Models Enable Zero-Shot Transliteration

ExPLAIND: Unifying Model, Data, and Training Attribution to Study Model Behavior

What’s the Difference? Supporting Users in Identifying the Effects of Prompt and Model Changes Through Token Patterns

Probing LLMs for Multilingual Discourse Generalization Through a Unified Label Set

Semantic Component Analysis: Introducing Multi-Topic Distributions to Clustering-Based Topic Modeling