Prompt engineering for text generation: Difference between revisions

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="”111”">Zhao et al. (2021) Calibrate Before Use: Improving Few-Shot Performance of Language Models arXiv:2102.09690</ref>

Liu et al. (2021) suggested choosing examples that are semantically similar to the test example by employing nearest neighbor (NN) clustering in the embedding space.

Su et al. (2022) proposed a graph-based approach to select a diverse and representative set of examples: (1) construct a directed graph based on the cosine similarity between samples in the embedding space (e.g., using SBERT or other embedding models), and (2) start with a set of selected samples and a set of remaining samples, scoring each sample to encourage diverse selection.

Rubin et al. (2022) suggested training embeddings through contrastive learning specific to one training dataset for in-context learning sample selection. This approach measures the quality of an example based on a conditioned probability assigned by the language model.

Zhang et al. (2022) explored using Q-Learning for sample selection in LLM training.

Diao et al. (2023) proposed identifying examples with high disagreement or entropy among multiple sampling trials based on uncertainty-based active learning. These examples can then be annotated and used in few-shot prompts.