Abstract: Rare language model behaviors can be difficult to study because obtaining them through ordinary sampling can require a very large number of samples. This motivates the behavior posterior sampling problem: given a language model and a behavior of interest, is there an algorithm that efficiently samples from the model's distribution over
[…]
Content was trimmed to protect the source. Please visit the original article for the full text.
Read the original article:
PosteriorBench: Evaluating Behavior Posterior Sampling in Language Models
