collaborators

6 papers

cs.CL2026

Copy First, Translate Later: Interpreting Translation Dynamics in Multilingual Pretraining

Felicia Körner, Maria Matveev, Florian Eichin +3

Large language models exhibit impressive cross-lingual capabilities. However, prior work analyzes this phenomenon through isolated factors and at sparse points during training, lim…

cs.LG2026

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

Florian Eichin, Yupei Du, Philipp Mondorf +3

Post-hoc interpretability methods typically attribute a model's behavior to its components, data, or training trajectory in isolation, and are often tied to a particular level of g…

cs.CL2026

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

Ryan Soh-Eun Shim, Kwanghee Choi, Kalvin Chang +8

Multilingual speech foundation models such as Whisper are trained on web-scale data, where data for each language consists of a myriad of regional varieties. However, different reg…

cs.CL2025

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

Florian Eichin, Carolin M. Schuster, Georg Groh +1

Topic modeling is a key method in text analysis, but existing approaches fail to efficiently scale to large datasets or are limited by assuming one topic per document. Overcoming t…

cs.CL2025

Probing LLMs for Multilingual Discourse Generalization Through a Unified Label Set

Florian Eichin, Yang Janet Liu, Barbara Plank +1

Discourse understanding is essential for many NLP tasks, yet most existing work remains constrained by framework-dependent discourse representations. This work investigates whether…

cs.CL2025

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

Michael A. Hedderich, Anyi Wang, Raoyuan Zhao +3

Prompt engineering for large language models is challenging, as even small prompt perturbations or model changes can significantly impact the generated output texts. Existing evalu…