2 papers
cs.CR2026
Black-box, Adaptive, Efficient, Transferable, Harmful, Applicable... Attacks Are All You Need to Break LLMs
Vincent Limbach, Jonas Dornbusch, David Lüdke +2
Accurately evaluating adversarial robustness is a longstanding challenge. A flawed attack design can inflate robustness estimates, making deployment risk assessment and defense com…
cs.CL2025
Regress, Don't Guess -- A Regression-like Loss on Number Tokens for Language Models
Jonas Zausinger, Lars Pennig, Anamarija Kozina +13
While language models have exceptional capabilities at text generation, they lack a natural inductive bias for emitting numbers and thus struggle in tasks involving quantitative re…