Vibeleaderboard
← All Intel
Intel / article

Chain-of-Thought Prompting Elicits Reasoning in Large Language Models

Source
arxiv.org
Author
Jason Wei et al.
Date

Context

The 2022 prompting paper tested whether examples that include intermediate reasoning steps help a solve a new problem. The prompt shows how to work toward an answer, giving the model a pattern to follow when generating its own response. Across three large models, the authors reported improvements on arithmetic, commonsense and symbolic reasoning tasks. Paper abstract.

One reported result used eight worked examples with a 540-billion-parameter model to achieve state-of-the-art accuracy at the time on GSM8K, a of math word problems. The finding concerns a particular prompting method under tested conditions: showing worked solutions can change task performance without those examples being used to retrain the model. Reported experiment.

Terms in this piece · Glossary
  • chain-of-thought — Having a model write out intermediate reasoning steps before its answer, which markedly improves performance on hard problems.
  • LLM — A large language model — the neural network behind tools like Claude and ChatGPT, trained on huge amounts of text to predict what comes next.
  • benchmark — A standard public test set for comparing AI models — the shared scoreboards behind every "model X beats model Y" claim.
Recommended reads
Comments

Checking sign-in…

Loading comments…