3 accepted papers
We investigate a family of simple long-context attacks on large language models: prompting with hundreds of demonstrations of undesirable behavior. This attack is newly feasible with the larger context windows recently deployed by language model providers like Google DeepMind, OpenAI and Anthropic.…
Conversational large language models are fine-tuned for both instruction-following and safety, resulting in models that obey benign requests but refuse harmful ones. While this refusal behavior is widespread across chat models, its underlying mechanisms remain poorly understood. In this work, we sho…
We introduce Contrastive Activation Addition (CAA), a method for steering language models by modifying their activations during forward passes. CAA computes “steering vectors” by averaging the difference in residual stream activations between pairs of positive and negative examples of a particular b…