Pith. sign in

More Samples or More Prompts? Exploring Effective In-Context Sampling for LLM Few-Shot Prompt Engineering

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it
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.

citation-role summary

baseline 1

citation-polarity summary

fields

cs.CL 1

years

2025 1

verdicts

REJECT 1

roles

baseline 1

polarities

baseline 1

representative citing papers

citing papers explorer

Showing 1 of 1 citing paper.