activity
20242026
collaborators
Showing cs.CLShow all

10 papers · 1 filter

cs.CL2026

Repetition over Diversity: High-Signal Data Filtering for Sample-Efficient German Language Modeling

Ansar Aynetdinov, Patrick Haller, Alan Akbik

Recent research has shown that filtering massive English web corpora into high-quality subsets significantly improves training efficiency. However, for high-resource non-English la…

cs.CL2026

What Matters in Linearizing Language Models? A Comparative Study of Architecture, Scale, and Task Adaptation

Patrick Haller, Jonas Golde, Alan Akbik

Linearization has emerged as a strategy for developing efficient language models (LMs). Starting from an existing Transformer-based LM, linearization replaces the attention compone…

cs.CL2026

What Matters When Building Universal Multilingual Named Entity Recognition Models?

Jonas Golde, Patrick Haller, Alan Akbik

Recent progress in universal multilingual named entity recognition (NER) has been driven by multilingual transformer models, task-specific architectures, custom loss functions, and…

cs.CL2025

FiNERweb: Datasets and Artifacts for Scalable Multilingual Named Entity Recognition

Jonas Golde, Patrick Haller, Alan Akbik

Recent multilingual named entity recognition (NER) work has shown that large language models (LLMs) can provide effective synthetic supervision, yet such datasets have mostly appea…

cs.CL2025

Sample-Efficient Language Modeling with Linear Attention and Lightweight Enhancements

Patrick Haller, Jonas Golde, Alan Akbik

We study architectural and optimization techniques for sample-efficient language modeling under the constraints of the BabyLM 2025 shared task. Our model, BLaLM, replaces self-atte…

cs.CL2025

LLM Knowledge is Brittle: Truthfulness Representations Rely on Superficial Resemblance

Patrick Haller, Mark Ibrahim, Polina Kirichenko +2

For Large Language Models (LLMs) to be reliable, they must learn robust knowledge that can be generally applied in diverse settings -- often unlike those seen during training. Yet,…