ASPIRE

A framework to enhance the selective prediction capability of large language models

CommonProductProductivityArtificial IntelligenceNatural Language Processing
ASPIRE is a well-designed framework designed to boost the selective prediction capability of large language models. It leverages parameter-efficient fine-tuning training to enable LLMs to self-assess and provide confidence scores for generated answers. Experimental results indicate that ASPIRE significantly outperforms current selective prediction methods on various question-answering datasets.
Visit

ASPIRE Visit Over Time

Monthly Visits

30653

Bounce Rate

57.71%

Page per Visit

1.4

Visit Duration

00:00:20

ASPIRE Visit Trend

ASPIRE Visit Geography

ASPIRE Traffic Sources

ASPIRE Alternatives