Language Models (Mostly) Know What They Knowwith Saurav Kadavath, Tom Conerly, Amanda Askell, Tom Henighan +312 versionsW_579nsf6fv2 · current
Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons LearnedW_rp4q6r33v2
Future Events as Backdoor Triggers: Investigating Temporal Vulnerabilities in LLMsSara Price, Arjun Panickssery, Sam Bowman et al.2 citations2407.04108v32024arXiv
Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons LearnedDeep Ganguli, Liane Lovitt, Jackson Kernion et al.127 citations2209.07858v22022arXivon Valency
Language Models (Mostly) Know What They KnowSaurav Kadavath, Tom Conerly, Amanda Askell et al.187 citations2207.05221v42022arXivon Valency
A Molecular Toolkit to Visualize Native Protein Assemblies in the Context of Human Disease.Gilmore, Brian L, Winton, Carly E, Demmert, Andrew C et al.16 citations263958232016Scientific reports. 2015;5:14440