Under the technique introduced by Wei et al. (2022) in "Chain-of-Thought Prompting Elicits Reasoning in Large Language Models," what does chain-of-thought prompting add to a standard few-shot prompt?
- It replaces the task examples with a single, more detailed instruction and removes all examples from the prompt
- It includes intermediate reasoning steps leading to the final answer within the few-shot exemplars, rather than showing only the input and final answer
- It requires retraining the model on a dataset of step-by-step solutions before it can be used
- It instructs the model to output only the final answer with no explanation, in order to reduce token usage and cost
Correct answer: B. It includes intermediate reasoning steps leading to the final answer within the few-shot exemplars, rather than showing only the input and final answer
Wei et al. (2022) show that augmenting few-shot exemplars with intermediate natural-language reasoning steps -- a "chain of thought" -- leading up to the final answer substantially improves performance on multi-step reasoning tasks, without any change to the model's weights. The first option is wrong because chain-of-thought prompting still uses worked examples; it enriches them with reasoning text rather than removing them in favor of a single instruction. The third option is wrong because the technique is applied at inference time to an already-trained, frozen model, not through a retraining or fine-tuning procedure on step-by-step solutions. The fourth option describes the opposite of the technique: chain-of-thought prompting deliberately elicits more explanatory reasoning text, not less, because that intermediate text is precisely what improves the accuracy of the final answer.
Source: Wei et al., "Chain-of-Thought Prompting Elicits Reasoning in Large Language Models" (2022), arXiv:2201.11903