conftrace_

jailbreak vulnerability

3 papers

Explore in graph

Co-occurring keywords · papers mentioning both

hidden context (1) inference-time search (1) safety-utility trade-off (1) borda count (1) token generation (1) fine-tuning attack (1) large vision-language model (1) adversarial attack (1) social choice (1) model alignment (1)

Papers

EcoAlign: An Economically Rational Framework for Efficient LVLM Alignment CVPR 2026 Safety Alignment Should be Made More Than Just a Few Tokens Deep ICLR 2025 Distributional Preference Learning: Understanding and Accounting for Hidden Context in RLHF ICLR 2024