Search Results for author:
Found 4 papers, 1 papers with code
Exploring the Robustness of Model-Graded Evaluations and Automated Interpretability
There has been increasing interest in evaluations of language models for a variety of risks and characteristics.
LoRA Fine-tuning Efficiently Undoes Safety Training in Llama 2-Chat 70B
With a budget of less than \$200 and using only one GPU, we successfully undo the safety training of Llama 2-Chat models of sizes 7B, 13B, and 70B and on the Mixtral instruct model.
BadLlama: cheaply removing safety fine-tuning from Llama 2-Chat 13B
Llama 2-Chat is a collection of large language models that Meta developed and released to the public.
Evaluating Shutdown Avoidance of Language Models in Textual Scenarios
Recently, there has been an increase in interest in evaluating large language models for emergent and dangerous capabilities.
