2 papers
cs.AI2026
Evaluation Awareness Beyond English: Do LLMs Act Differently When Tested in Indic Languages?
Trizal Garg, Sibayan Mitra, Arya Karanjkar +6
Large language models (LLMs) can often tell when they are being tested. This ability, known as evaluation awareness, can lead models to act more cautiously during safety evaluation…
cs.CR2025
Do You Really Need a GPU to Guard Your LLM? CPU-Class Classifiers and Multi-Stage Pipelines for Safety Enforcement at Scale
Vasudev Majhi, Dhruv Gupta, Advait Singh +2
Safety classifiers that screen LLM inputs for jailbreak attempts have become standard deployment components, yet almost all production systems rely on GPU-based models: fine-tuned…