FineWeb-CLaR is introduced, a large-scale annotated dataset derived from FineWeb and FineWeb-2 that places web documents on a shared culture-language-region axis for corpus auditing and benchmark alignment, enabling direct comparison between corpus-side pretraining evidence and benchmark-side evaluation coverage.
Yusser Al Ghussin, Eva Gavaller, Cristina España-Bonet et al.· 0 citations
In an age marked by global crises, a transcultural understanding of the philosophical foundations of human thought—especially in epistemology and ethics—has become essential. Contemporary ecological crises unfold on a planetary scale, exceeding both the conceptual limits of nation-states and the historically constitut...
Jana S. Rošker, R. Pozzo, Marko Robnik Šikonja et al.· Asian Studies· 0 citations
This study examines the compositionality of steering vectors for language and behavioral control in large language models. Focusing on language, jailbreak, and conciseness, we investigate whether additive, training-free composition of attribute steering vectors can preserve the intended steering effect of each attribut...
Hyunku Kang, Daniil Gurgurov, Tanja Baeumel et al.· 0 citations
To investigate internal mechanisms of linear probing, attribution patching, sparse autoencoders and feature ablation in Llama-3.1-8B, Qwen3-8B, and Gemma-2-9B, linear probing performance peaks substantially earlier than attribution in all three models.
Ariun-Erdene Tumurchuluun, Yusser Al Ghussin, Pinzhen Chen et al.· 0 citations
It is argued that framing tokenization as output supervision provides a principled account of why tokenization consistently affects model performance, and that differences in task performance, training dynamics, and model internals are induced by output tokenization and largely invariant to input tokenization.
Tanja Baeumel, Josef van Genabith, Simon Ostermann· 0 citations
It is shown that translation is even more modular than previously assumed and that the output language production in translation processes is actually further separable into a syntax and a surface language process.
M. Sonkin, Tanja Baeumel, Daniil Gurgurov et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
