14 papers
ActivationReasoning: Logical Reasoning in Latent Activation Spaces
Lukas Helff, Ruben Härle, Wolfgang Stammer +6
Large language models (LLMs) excel at generating fluent text, but their internal reasoning remains opaque and difficult to control. Sparse autoencoders (SAEs) make hidden activatio…
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…
UniFusion: Vision-Language Model as Unified Encoder in Image Generation
Kevin Li, Manuel Brack, Sudeep Katakol +2
Although recent advances in visual generation have been remarkable, most existing architectures still depend on distinct encoders for images and text. This separation constrains di…
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…
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…
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…