Jump to content

Oracle international corporation (20250094138). LLM FINE-TUNING FOR CODE GENERATION

From WikiPatents

LLM FINE-TUNING FOR CODE GENERATION

Organization Name

oracle international corporation

Inventor(s)

Yazhe Hu of Bellevue WA US

Mengqing Guo of Issaquah WA US

Zheng Wang of Sammamish WA US

Tao Sheng of Bellevue WA US

Jun Qian of Newcastle WA US

Vinod Mamtani of Bellevue WA US

LLM FINE-TUNING FOR CODE GENERATION

This abstract first appeared for US patent application 20250094138 titled 'LLM FINE-TUNING FOR CODE GENERATION

Original Abstract Submitted

systems, methods, and other embodiments associated with automated fine-tuning of software code generation by large language models are described herein. in one embodiment, a method accesses a collection of software code samples that intermix sample code and human language description. the method generates prompts to an llm to write code that performs as described by the human language description of the sample code. the method fine-tunes a large language model to generate software code based on a code generation loss function that evaluates code generated by the llm in response to the prompts. the method generates an evaluation score for performance of the tuned large language model as a code generator based on code generation loss for second generated code. and, the method automatically signals that fine-tuning of the tuned large language is complete in response to the evaluation score satisfying a threshold.

Cookies help us deliver our services. By using our services, you agree to our use of cookies.