18498988. CONTRASTIVE IN-CONTEXT LEARNING FOR LARGE LANGUAGE MODELS (INTUIT INC.)

CONTRASTIVE IN-CONTEXT LEARNING FOR LARGE LANGUAGE MODELS

Organization Name

INTUIT INC.

Inventor(s)

Xiang Gao of Mountain View CA US

Kamalika Das of Mountain View CA US

CONTRASTIVE IN-CONTEXT LEARNING FOR LARGE LANGUAGE MODELS

This abstract first appeared for US patent application 18498988 titled 'CONTRASTIVE IN-CONTEXT LEARNING FOR LARGE LANGUAGE MODELS

Original Abstract Submitted

A contrastive in-context learning protocol for large language models. The protocol includes inputting positive and negative examples to a large language model. Additionally, the large language model may be instructed to analyze the reasons behind the positive examples being positive and the negative examples being negative. The large language model with such contrastive in-context learning can generate specific responses/answers based on user preferences, generally not possible using conventional models.