1 citations · 3 across the 10 of their papers we have counts for
4 papers · 1 filter
Can LLMs subtract numbers?
Mayank Jobanputra, Nils Philipp Walter, Maitrey Mehta +7
We present a systematic study of subtraction in large language models (LLMs). While prior benchmarks emphasize addition and multiplication, subtraction has received comparatively l…
When Flatness Does (Not) Guarantee Adversarial Robustness
Nils Philipp Walter, Linara Adilova, Jilles Vreeken +1
Despite their empirical success, neural networks remain vulnerable to small, adversarial perturbations. A longstanding hypothesis suggests that flat minima, regions of low curvatur…
Soft Instruction De-escalation Defense
Nils Philipp Walter, Chawin Sitawarin, Jamie Hayes +2
Large Language Models (LLMs) are increasingly deployed in agentic systems that interact with an external environment; this makes them susceptible to prompt injections when dealing…
Hidden in Plain Sight -- Class Competition Focuses Attribution Maps
Nils Philipp Walter, Jilles Vreeken, Jonas Fischer
Attribution methods reveal which input features a neural network uses for a prediction, adding transparency to their decisions. A common problem is that these attributions seem uns…