Search Results for author:
Found 2 papers, 1 papers with code
Forbidden Facts: An Investigation of Competing Objectives in Llama-2
LLMs often face competing pressures (for example helpfulness vs. harmlessness).
Diagnostics for Deep Neural Networks with Automated Copy/Paste Attacks
Some previous works have proposed using human-interpretable adversarial attacks including copy/paste attacks in which one natural image pasted into another causes an unexpected misclassification.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
