Search Results for author:
Found 2 papers, 0 papers with code
Immunization against harmful fine-tuning attacks
Approaches to aligning large language models (LLMs) with human values has focused on correcting misalignment that emerges from pretraining.
Explaining Learned Reward Functions with Counterfactual Trajectories
Finally, we measure how informative the generated explanations are to a proxy-human model by training it on CTEs.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
