565 citations · 734 across the 71 of their papers we have counts for
Showing cs.AIShow all
2 papers · 1 filter
cs.AI2026
LEMON: Equivariant Learning over Attention Maps for Zero-Shot Misbehavior Monitoring on New LLMs
Guy Bar-Shalom, Mor Geva, Fabrizio Frasca +1
Large language models exhibit misbehaviors that hinder deployment in high-stakes settings. One approach to monitor such failures is to use an external LLM as a monitor, but this is…
cs.AI2026
The Safety Operator: Modulating the Expression of Safety Instructions via Spectral Optimization
Benoit Dherin, Michael Munn, Xavier Gonzalvo +14
Context tokens in a transformer-based language model can be absorbed into the model's weights as a multiplicative operator. We study this operator in the setting of safety instruct…