More Samples or More Prompts? Exploring Effective Few-Shot In-Context Learning for LLMs with In-Context Sampling
No Thumbnail Available
Authors
Yao, Bingsheng
Chen, Guiming
Zou, Ruishi
Lu, Yuxuan
Li, Jiachen
Zhang, Shao
Sang, Yisi
Liu, Sijia
Hendler, James A.
Wang, Dakuo
Issue Date
2024-06-01
Type
Article
Language
Keywords
Alternative Title
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.
Description
Full Citation
Bingsheng Yao, Guiming Chen, Ruishi Zou, Yuxuan Lu, Jiachen Li, Shao Zhang, Yisi Sang, Sijia Liu, James Hendler, and Dakuo Wang. 2024. More Samples or More Prompts? Exploring Effective Few-Shot In-Context Learning for LLMs with In-Context Sampling. In Findings of the Association for Computational Linguistics: NAACL 2024, pages 1772–1790, Mexico City, Mexico. Association for Computational Linguistics.
Publisher
ACL Anthology