MUMBAI, India, July 31 -- Intellectual Property India has published a patent application (202411097728 A) filed by Fujitsu Limited on December 11, 2024, for Method And Apparatus For Large Language Model Output Filtering.
Inventors include Padakandla, Sindhu; Babar, Sadbhavana; Rathod, Darshan Dineshkumar; and Kaul, Manohar.
The application for the patent was published on July 24, 2026, under issue no. 30/2026.
Abstract: A computer-implemented method of training a filter for large language model, LLM, outputs, the method comprising: accepting input of a plurality of training prompts, the plurality of training prompts comprising labels identifying each prompt as a safe prompt or an unsafe prompt; for each training prompt, obtaining a plurality of LLM parameter gradients by passing the training prompt through an LLM selecting a subset of the plurality of LLM parameter gradients, and quantizing the subset to obtain quantized gradient information; and training a classifier using the quantized gradient information and the training prompt labels, the trained classifier being configured to act as the filter for LLM outputs and classify prompts as safe or unsafe.
Disclaimer: Curated by HT Syndication.
