AI & Machine Learning Meetup: Automatic Prompt Optimization with “Gradient Descent” and Beam Search скачать в хорошем качестве

AI & Machine Learning Meetup: Automatic Prompt Optimization with “Gradient Descent” and Beam Search

Large Language Models (LLMs) have shown impressive performance but their abilities remain highly dependent on prompts which are hand written with onerous trial-and-error effort. We propose a simple and nonparametric solution to this problem, Automatic Prompt Optimization (APO), which is inspired by numerical gradient descent to automatically improve prompts, assuming access to training data and an LLM API. Our experiments suggest this method can outperform prior prompt editing techniques and improve an initial prompt’s performance by up to 31%, by using data to rewrite vague task descriptions into more precise annotation instructions. Reid Pryzant is a Senior Research Scientist at Microsoft, and former Computer Science PhD at Stanford University advised by Dan Jurafsky. His work has won outstanding research awards from CVPR, AAAI, and the National Science Foundation. Paper: Automatic Prompt Optimization with "Gradient Descent" and Beam Search - https://arxiv.org/abs/2305.03495 Not a Meetup member? Scroll down on this page and join the Computer Vision Meetup friendliest to your timezone: https://www.meetup.com/pro/ai-machine... Recorded on Oct 5, 2023 at the virtual AI, Machine Learning and Data Science Meetup. #computervision #machinelearning #datascience #ai #artificialintelligence