activity
20242026
collaborators
Showing cs.CLShow all

7 papers · 1 filter

cs.CL2025

Measuring and Guiding Monosemanticity

Ruben Härle, Felix Friedrich, Manuel Brack +4

There is growing interest in leveraging mechanistic interpretability and controllability to better understand and influence the internal dynamics of large language models (LLMs). H…

cs.CL2025

CHRONOBERG: Capturing Language Evolution and Temporal Awareness in Foundation Models

Niharika Hegde, Subarnaduti Paul, Lars Joel-Frey +4

Large language models (LLMs) excel at operating at scale by leveraging social media and various data crawled from the web. Whereas existing corpora are diverse, their frequent lack…

cs.CL2025

Beyond Overcorrection: Evaluating Diversity in T2I Models with DivBench

Felix Friedrich, Thiemo Ganesha Welsch, Manuel Brack +2

Current diversification strategies for text-to-image (T2I) models often ignore contextual appropriateness, leading to over-diversification where demographic attributes are modified…

cs.CL2025

LLMs Lost in Translation: M-ALERT uncovers Cross-Linguistic Safety Inconsistencies

Felix Friedrich, Simone Tedeschi, Patrick Schramowski +5

Building safe Large Language Models (LLMs) across multiple languages is essential in ensuring both safe access and linguistic diversity. To this end, we conduct a large-scale, comp…

cs.CL2025

Judging Quality Across Languages: A Multilingual Approach to Pretraining Data Filtering with Language Models

Mehdi Ali, Manuel Brack, Max Lübbering +15

High-quality multilingual training data is essential for effectively pretraining large language models (LLMs). Yet, the availability of suitable open-source multilingual datasets r…

cs.CL2025

T-FREE: Subword Tokenizer-Free Generative LLMs via Sparse Representations for Memory-Efficient Embeddings

Björn Deiseroth, Manuel Brack, Patrick Schramowski +2

Tokenizers are crucial for encoding information in Large Language Models, but their development has recently stagnated, and they contain inherent weaknesses. Major limitations incl…