The benchmark comprises of 161 programming problems One common approach is training models to refuse unsafe queries, but this strategy can be vulnerable to clever prompts, often referred to as jailbreak attacks, which can trick the ai into providing harmful responses Our analysis yields a novel robustness metric called clever, which is short for cross lipschitz extreme value for network robustness
Joni Rose on Instagram: “Urs🐇😉” | Joni, Instagram, Rose
Across evaluated tasks, rahp yields compact models with stronger clever lower bounds and minimal change in clean accuracy, and it improves resistance to a wide variety of strong attacks
With a clever usage of the equivalence between reward models and the corresponding optimal policy, the algorithm features a simple objective that combines (i) a preference optimization loss that directly aligns the policy with human preference, and (ii) a supervised learning loss which explicitly imitates the policy with a baseline distribution.
