English

Boosted Prompt Ensembles for Large Language Models

Computation and Language 2023-04-13 v1 Machine Learning

Abstract

Methods such as chain-of-thought prompting and self-consistency have pushed the frontier of language model reasoning performance with no additional training. To further improve performance, we propose a prompt ensembling method for large language models, which uses a small dataset to construct a set of few shot prompts that together comprise a ``boosted prompt ensemble''. The few shot examples for each prompt are chosen in a stepwise fashion to be ``hard'' examples on which the previous step's ensemble is uncertain. We show that this outperforms single-prompt output-space ensembles and bagged prompt-space ensembles on the GSM8k and AQuA datasets, among others. We propose both train-time and test-time versions of boosted prompting that use different levels of available annotation and conduct a detailed empirical study of our algorithm.

Keywords

Cite

@article{arxiv.2304.05970,
  title  = {Boosted Prompt Ensembles for Large Language Models},
  author = {Silviu Pitis and Michael R. Zhang and Andrew Wang and Jimmy Ba},
  journal= {arXiv preprint arXiv:2304.05970},
  year   = {2023}
}
R2 v1 2026-06-28T10:02:34.003Z