Quantifying Behavioral Tails in Black-Box Language Models
We introduce RareTrap, a framework for estimating the probability of severe behaviors in black box large language models (LLMs). A key challenge for probability estimation is defining a tractable distribution over the input space. To accomplish that, RareTrap uses a surrogate LLM and constructs a geometry-aware mapping...
Elsayed Eshra, Ali Al-Lawati, Dongwon Lee et al.
· 0 citations