Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
This addresses the challenge of enhancing reasoning capabilities in large language models for applications requiring complex problem-solving, representing a notable advance rather than an incremental improvement.
The paper tackles the problem of improving complex reasoning in large language models by introducing chain-of-thought prompting, which involves generating intermediate reasoning steps, and shows that this method significantly boosts performance on tasks like arithmetic and commonsense reasoning, achieving state-of-the-art accuracy on the GSM8K benchmark with a 540B-parameter model.
We explore how generating a chain of thought -- a series of intermediate reasoning steps -- significantly improves the ability of large language models to perform complex reasoning. In particular, we show how such reasoning abilities emerge naturally in sufficiently large language models via a simple method called chain of thought prompting, where a few chain of thought demonstrations are provided as exemplars in prompting. Experiments on three large language models show that chain of thought prompting improves performance on a range of arithmetic, commonsense, and symbolic reasoning tasks. The empirical gains can be striking. For instance, prompting a 540B-parameter language model with just eight chain of thought exemplars achieves state of the art accuracy on the GSM8K benchmark of math word problems, surpassing even finetuned GPT-3 with a verifier.