all AI news
STaR: Bootstrapping Reasoning With Reasoning. (arXiv:2203.14465v2 [cs.LG] UPDATED)
May 23, 2022, 1:12 a.m. | Eric Zelikman, Yuhuai Wu, Jesse Mu, Noah D. Goodman
cs.CL updates on arXiv.org arxiv.org
Generating step-by-step "chain-of-thought" rationales improves language model
performance on complex reasoning tasks like mathematics or commonsense
question-answering. However, inducing language model rationale generation
currently requires either constructing massive rationale datasets or
sacrificing accuracy by using only few-shot inference. We propose a technique
to iteratively leverage a small number of rationale examples and a large
dataset without rationales, to bootstrap the ability to perform successively
more complex reasoning. This technique, the "Self-Taught Reasoner" (STaR),
relies on a simple loop: generate rationales …
More from arxiv.org / cs.CL updates on arXiv.org
Jobs in AI, ML, Big Data
Data Engineer
@ Bosch Group | San Luis Potosí, Mexico
DATA Engineer (H/F)
@ Renault Group | FR REN RSAS - Le Plessis-Robinson (Siège)
Advisor, Data engineering
@ Desjardins | 1, Complexe Desjardins, Montréal
Data Engineer Intern
@ Getinge | Wayne, NJ, US
Software Engineer III- Java / Python / Pyspark / ETL
@ JPMorgan Chase & Co. | Jersey City, NJ, United States
Lead Data Engineer (Azure/AWS)
@ Telstra | Telstra ICC Bengaluru