BigDocs: An Open and Permissively-Licensed Dataset for Training Multimodal Models on Document and Code Tasks Paper • 2412.04626 • Published Dec 5, 2024 • 13
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
Hallucination Detox: Sensitive Neuron Dropout (SeND) for Large Language Model Training Paper • 2410.15460 • Published Oct 20, 2024 • 1
Open, Closed, or Small Language Models for Text Classification? Paper • 2308.10092 • Published Aug 19, 2023
Scavenging Hyena: Distilling Transformers into Long Convolution Models Paper • 2401.17574 • Published Jan 31, 2024 • 15