-
Large Language Models Are Zero-Shot Time Series Forecasters
Abstract of publication By encoding time series as a string of numerical digits, we can frame time series forecasting as next-token prediction in text. Developing this approach, we find that large language models (LLMs) such as GPT-3 and LLaMA-2 can surprisingly zeroshot extrapolate time series at a level comparable to or exceeding the performance of…
-
Large Language Models
Abstract of publication Dictionary definitions are historically the arbitrator of what words mean, but this primacy has come under threat by recent progress in NLP, including word embeddings and generative models like ChatGPT. We present an exploratorystudy of the degree of alignment between word definitions from classical dictionaries and these newer computational artifacts. Specifically, we…