370
edits
Prompt engineering for text generation: Difference between revisions
Prompt engineering for text generation (view source)
Revision as of 16:28, 5 April 2023
, 5 April 2023→Advanced
| Line 129: | Line 129: | ||
In few-shot prompting, the model is presented with high-quality demonstrations, including input and desired output, for the target task. This approach enables the model to understand the human intention better and the desired criteria for answers, often resulting in improved performance compared to zero-shot prompting. However, this comes at the expense of increased token consumption and may reach the context length limit for longer input and output texts. | In few-shot prompting, the model is presented with high-quality demonstrations, including input and desired output, for the target task. This approach enables the model to understand the human intention better and the desired criteria for answers, often resulting in improved performance compared to zero-shot prompting. However, this comes at the expense of increased token consumption and may reach the context length limit for longer input and output texts. | ||
Numerous studies have explored how to construct in-context examples to maximize performance. Prompt format, training examples, and example order can lead to dramatically different performance outcomes, ranging from near-random guessing to near state-of-the-art (SoTA) results. | Numerous studies have explored how to construct in-context examples to maximize performance. [[Prompt format]], [[training examples]], and [[example order]] can lead to dramatically different performance outcomes, ranging from near-random guessing to near state-of-the-art (SoTA) results. | ||
Zhao et al. (2021) investigated few-shot classification using LLMs, specifically GPT-3. They identified several biases that contribute to high variance in performance: (1) majority label bias, (2) recency bias, and (3) common token bias. To address these biases, they proposed a method to calibrate label probabilities output by the model to be uniform when the input string is N/A. | Zhao et al. (2021) investigated [[few-shot classification]] using LLMs, specifically [[GPT-3]]. They identified several biases that contribute to high [[variance]] in performance: (1) majority [[label bias]], (2) [[recency bias]], and (3) [[common token bias]]. To address these [[biases]], they proposed a method to calibrate label probabilities output by the model to be uniform when the input string is N/A.<ref name="11">https://arxiv.org/abs/2102.09690</ref> | ||
====Tips for Example Selection==== | ====Tips for Example Selection==== | ||