COMBINATORIAL PROMPTING FOR LARGE LANGUAGE MODELS

Number of patents in Portfolio can not be more than 2000

United States of America Patent

APP PUB NO 20250103624A1
SERIAL NO

18473808

Stats

ATTORNEY / AGENT: (SPONSORED)

Importance

Loading Importance Indicators... loading....

Abstract

See full text

An embodiment for generating and employing incrementally optimized combinatorial prompts for tuning a target model. The embodiment may select a predetermined number of examples from a training dataset. The embodiment may concatenate each of the selected examples with a current prompt of a target model to obtain a set of candidate prompts. The embodiment may, for each individual candidate prompt in the set of candidate prompts, calculate a loss value over a validation dataset. The embodiment may replace the current prompt with the individual candidate prompt having a lowest calculated loss value that is less than or equal to an original loss value over the validation set for the current prompt to obtain an updated prompt.

Loading the Abstract Image... loading....

First Claim

See full text

Family

Loading Family data... loading....

Patent Owner(s)

Patent OwnerAddress
INTERNATIONAL BUSINESS MACHINES CORPORATIONNEW ORCHARD ROAD ARMONK NY 10504

International Classification(s)

  • [Classification Symbol]
  • [Patents Count]

Inventor(s)

Inventor Name Address # of filed Patents Total Citations
Agravante, Don Joven Ravoy Yamato, JP 11 9
Carta, Thomas Andre Maxime Bordeaux, FR 1 0
Kimura, Daiki Midori-ku, JP 21 42
Tatsubori, Michiaki Oiso, JP 94 1388

Cited Art Landscape

Load Citation

Patent Citation Ranking

Forward Cite Landscape

Load Citation