The benchmark comprises of 161 programming problems Our method, stair (safety alignment with introspective reasoning), guides models to think more carefully before responding. Our analysis yields a novel robustness metric called clever, which is short for cross lipschitz extreme value for network robustness
Zac (@thezacattack_) • Threads, Say more
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
Back in the early 20th century, a horse named hans appeared to perform arithmetic and other intellectual tasks during exhibitions in germany, while it actually relied solely on involuntary cues in.
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
