Mila CDL PRM

classroom

AI & ML interests

None defined yet.

Recent Activity

kellinpelrine authored a paper about 2 months ago

Comparing GPT-4 and Open-Source Language Models in Misinformation Mitigation

kellinpelrine authored a paper about 2 months ago

Emerging Vulnerabilities in Frontier Models: Multi-Turn Jailbreak Attacks

kellinpelrine authored a paper 5 months ago

Exploiting Novel GPT-4 APIs

View all activity

mila-cdl-prm's activity

kellinpelrine

authored 2 papers about 2 months ago

Comparing GPT-4 and Open-Source Language Models in Misinformation Mitigation

Paper • 2401.06920 • Published Jan 12, 2024

Emerging Vulnerabilities in Frontier Models: Multi-Turn Jailbreak Attacks

Paper • 2409.00137 • Published Aug 29, 2024

kellinpelrine

authored 3 papers 5 months ago

Exploiting Novel GPT-4 APIs

Paper • 2312.14302 • Published Dec 21, 2023 • 12

Open, Closed, or Small Language Models for Text Classification?

Paper • 2308.10092 • Published Aug 19, 2023

Adversarial Policies Beat Superhuman Go AIs

Paper • 2211.00241 • Published Nov 1, 2022

jacobthebanana

updated a dataset about 1 year ago

mila-cdl-prm/20240107a1-gsm8k-contrastive-vicuna_7b_v1.5

Preview • Updated Jan 7, 2024 • 1