conftrace_

safety margin

2 papers

Explore in graph

Co-occurring keywords · papers mentioning both

coupled noise design (1) feasible action search (1) random perturbation (1) large language model (1) preference dataset (1) harmless alignment (1) representation engineering (1) linear bandit (1) reward model (1) thompson sampling (1)

Papers

Feasible Action Search for Bandit Linear Programs via Thompson Sampling ICML 2025 LEGEND: Leveraging Representation Engineering to Annotate Safety Margin for Preference Datasets AAAI 2025