NEFTune: Noisy Embeddings Improve Instruction Finetuning Paper • 2310.05914 • Published Oct 9, 2023 • 13
Spotting LLMs With Binoculars: Zero-Shot Detection of Machine-Generated Text Paper • 2401.12070 • Published Jan 22 • 40
Does Circuit Analysis Interpretability Scale? Evidence from Multiple Choice Capabilities in Chinchilla Paper • 2307.09458 • Published Jul 18, 2023 • 9