40 citations · 72 across the 18 of their papers we have counts for
Showing 2026Show all
2 papers · 1 filter
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…
cs.LG2026
Grow, Don't Overwrite: Fine-tuning Without Forgetting
Dyah Adila, Hanna Mazzawi, Benoit Dherin +1
Adapting pre-trained models to specialized tasks often leads to catastrophic forgetting, where new knowledge overwrites foundational capabilities. Existing methods either compromis…