x.com
Gonçalo Faria on X: "Introducing 𝗤𝗔𝗹𝗶𝗴𝗻🚀, a 𝘁𝗲𝘀𝘁-𝘁𝗶𝗺𝗲 𝗮𝗹𝗶𝗴𝗻𝗺𝗲𝗻𝘁 𝗺𝗲𝘁𝗵𝗼𝗱 that improves language model performance using Markov chain Monte Carlo. With no model retraining, 𝗤𝗔𝗹𝗶𝗴𝗻 outperforms DPO-tuned models even when allowed to match inference compute, and achieves https://t.co/XbstsJhO0c" / X
Introducing 𝗤𝗔𝗹𝗶𝗴𝗻🚀, a 𝘁𝗲𝘀𝘁-𝘁𝗶𝗺𝗲 𝗮𝗹𝗶𝗴𝗻𝗺𝗲𝗻𝘁 𝗺𝗲𝘁𝗵𝗼𝗱 that improves language model performance using Markov chain Monte Carlo. With no model retraining, 𝗤𝗔𝗹𝗶𝗴𝗻 outperforms DPO-tuned models even when allowed to match inference compute, and achieves https://t.co/XbstsJhO0c
