Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
PatchBench: Measuring Collateral Damage in Activation Patching
Alexi Canesse, Mathis Le Bail, Maël Jenny +3
An LLM safety patch can pass a benchmark while still being a poor repair. This risk is especially acute for jailbreak repairs, where the goal is to correct a specific unsafe behavi…
cs.LG2026
Reformulation-Contrastive Learning for Mixed Integer Programs
Ousema Bouaneni, Mathis Le Bail, Clément Elliker +2
Mixed-integer linear programs (MILP) model many real-world decision problems, motivating machine-learning methods that exploit recurring structure to accelerate MILP solving. MILPs…