Comparing GPT-4 and Open-Source Language Models in Misinformation Mitigation
Paper • 2401.06920 • Published
Kellin Pelrine
kellinpelrine
AI & ML interests
None yet
Organizations
authored 5
papers over 1 year ago
Emerging Vulnerabilities in Frontier Models: Multi-Turn Jailbreak Attacks
Paper • 2409.00137 • Published
Exploiting Novel GPT-4 APIs
Paper • 2312.14302 • Published • 14
Open, Closed, or Small Language Models for Text Classification?
Paper • 2308.10092 • Published
Adversarial Policies Beat Superhuman Go AIs
Paper • 2211.00241 • Published