NAACL 2024findings11 citations

More Samples or More Prompts? Exploring Effective Few-Shot In-Context Learning for LLMs with In-Context Sampling

Bingsheng Yao, Guiming Chen, Ruishi Zou, Yuxuan Lu, Jiachen Li, Shao Zhang, Yisi Sang, Sijia Liu

Abstract

While most existing works on LLM prompting techniques focus only on how to select a better set of data samples inside one single prompt input (In-Context Learning or ICL), why can not we design and leverage multiple prompts together to further improve the LLM’s performance? In this work, we propose In-Context Sampling (ICS), a low-resource LLM prompting technique to produce confident predictions by optimizing the construction of multiple ICL prompt inputs. Extensive experiments with three open-source LLMs (FlanT5-XL, Mistral-7B, and Mixtral-8x7B) on four NLI datasets (e-SNLI, Multi-NLI, ANLI, and Contract-NLI) and one QA dataset (CommonsenseQA) illustrate that ICS can consistently enhance LLMs’ performance. An in-depth evaluation with three data similarity-based ICS strategies suggests that these strategies can further elevate LLM’s performance, which sheds light on a new yet promising future research direction.

BibTeX
@inproceedings{yao-etal-2024-samples,
    title = "More Samples or More Prompts? Exploring Effective Few-Shot In-Context Learning for {LLM}s with In-Context Sampling",
    author = "Yao, Bingsheng  and
      Chen, Guiming  and
      Zou, Ruishi  and
      Lu, Yuxuan  and
      Li, Jiachen  and
      Zhang, Shao  and
      Sang, Yisi  and
      Liu, Sijia  and
      Hendler, James  and
      Wang, Dakuo",
    editor = "Duh, Kevin  and
      Gomez, Helena  and
      Bethard, Steven",
    booktitle = "Findings of the Association for Computational Linguistics: NAACL 2024",
    month = jun,
    year = "2024",
    address = "Mexico City, Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2024.findings-naacl.115/",
    doi = "10.18653/v1/2024.findings-naacl.115",
    pages = "1772--1790"
}
More Samples or More Prompts? Exploring Effective Few-Shot In-Context Learning for LLMs with In-Context Sampling · NAACL 2024