English

UPRISE: Universal Prompt Retrieval for Improving Zero-Shot Evaluation

Computation and Language 2023-12-19 v4

Abstract

Large Language Models (LLMs) are popular for their impressive abilities, but the need for model-specific fine-tuning or task-specific prompt engineering can hinder their generalization. We propose UPRISE (Universal Prompt Retrieval for Improving zero-Shot Evaluation), which tunes a lightweight and versatile retriever that automatically retrieves prompts for a given zero-shot task input. Specifically, we demonstrate universality in a cross-task and cross-model scenario: the retriever is tuned on a diverse set of tasks, but tested on unseen task types; we use a small frozen LLM, GPT-Neo-2.7B, for tuning the retriever, but test the retriever on different LLMs of much larger scales, such as BLOOM-7.1B, OPT-66B and GPT3-175B. Additionally, we show that UPRISE mitigates the hallucination problem in our experiments with ChatGPT, suggesting its potential to improve even the strongest LLMs. Our model and code are available at https://github.com/microsoft/LMOps.

Keywords

Cite

@article{arxiv.2303.08518,
  title  = {UPRISE: Universal Prompt Retrieval for Improving Zero-Shot Evaluation},
  author = {Daixuan Cheng and Shaohan Huang and Junyu Bi and Yuefeng Zhan and Jianfeng Liu and Yujing Wang and Hao Sun and Furu Wei and Denvy Deng and Qi Zhang},
  journal= {arXiv preprint arXiv:2303.08518},
  year   = {2023}
}

Comments

EMNLP 2023 Main Conference

R2 v1 2026-06-28T09:18:13.299Z