Intellectual Property India Publishes Patent Application for 'Few-Shot Adaptation System For Text Summarization Using Large Language Models' Filed by Vellore Institute Of Technology

MUMBAI, India, Jan. 2 -- Intellectual Property India has published a patent application (202541122100 A) filed by Vellore Institute Of Technology, Vellore, Tamil Nadu, on Dec. 4, 2025, for 'few-shot adaptation system for text summarization using large language models.'

Inventor(s) include Dr. Gunasekar M; Yash Kumar; Sanjay Haritwal; and Bhavya Sharma.

The application for the patent was published on Jan. 2, under issue no. 01/2026.

According to the abstract released by the Intellectual Property India: "The present disclosure provides a few-shot adaptation system for text summarization using large language models. The system includes a preprocessing module configured to create few-shot prompts by incorporating a predetermined small number of example input-output pairs with input text, a model handler module configured to load and manage multiple large language models with a unified interface, a parameter-efficient fine-tuning module configured to adapt the large language models using selective parameter modification techniques that update only a small fraction of original model parameters, and an inference engine configured to generate text summaries by processing the few-shot prompts through an adapted large language model. The preprocessing module, the model handler module, the parameter-efficient fine-tuning module, and the inference engine are interconnected to form a pipeline for few-shot adaptation."

Disclaimer: Curated by HT Syndication.