Showing cs.CLShow all
2 papers · 1 filter
cs.CL2026
On Mitigation of Subliminal Learning in Large Language Models
Atsushi Yanagisawa, Brendan Gho, Rajendran Ramesh Babu Manoj Narender +3
Knowledge distillation can transmit unintended behavioral traits from a teacher model to a student through training data that appear semantically unrelated to those traits, a pheno…
cs.CL2025
Probe-Rewrite-Evaluate: A Workflow for Reliable Benchmarks and Quantifying Evaluation Awareness
Lang Xiong, Nishant Bhargava, Jianhang Hong +4
Large Language Models (LLMs) often exhibit significant behavioral shifts when they perceive a change from a real-world deployment context to a controlled evaluation setting, a phen…