Author
German Research Center for Artificial Intelligence (DFKI)
We have 4 of 16 papers
We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.
Not the right person? Other researchers publish under this name.
By structurally decoupling abstract judging from output formatting, this work provides a mechanistic account of format-induced inconsistency on the open-weight models the authors study and implies that benchmark comparisons of judge reliability across formats partly measure the fragile formatting stage, and can underst...
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...
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.
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.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
