/Patent Tracker
GooglePatent applicationAI & softwareInterest 6/10

Google patents method to make AI models follow instructions more efficiently

Google describes a system where one AI model generates an answer and a second AI model checks it against the user's specific instructions. The system then refines the answer and saves the feedback to help improve the model's ability to follow rules in the future.

Why it mattersThis approach aims to reduce the computing power needed for AI to accurately follow complex user commands by using a self-checking process.

In the filing’s own words

Implementations relate to improving instruction following capabilities of large language models (LLMs) using instruction decomposition, self-evaluation, and optionally progressive refinement. Processor(s) of a system can: obtain natural language (NL) based input, generate a plurality of candidate responses and evaluate the candidate responses based on instructions included in the NL based input, using an LLM, and progressively refine the candidate responses until it is determined that one or more termination criteria are satisfied. In some implementations, the NL based input can be received from a client device. In these implementations, a given candidate response that is progressively refined can be rendered for presentation at the client device and responsive to the NL base input. In additional or alternative implementations, the NL based input can be obtained from database(s). In these implementations, a given candidate response that is progressively refined can be utilized in fine-tuning of the LLM.

What exactly they claim (claim 1)

1. A method implemented by one or more processors, the method comprising: obtaining natural language (NL) based input and a candidate response that is responsive to the NL based input, the candidate response being generated using a first large language model (LLM); identifying a set of instructional constraints included in the NL based input; generating, using a second LLM that differs from the first LLM, a critique response for the candidate response, the critique response including a reference to one or more specific portions of the candidate response to indicate compliance or violation with respect to at least one instructional constraint from the set of instructional constraints; and storing a training instance, the training instance including the NL based input, the candidate response, and the critique response.

Facts

Company
Google (GOOGLE LLC)
Official title
INSTRUCTION FOLLOWING IN LARGE LANGUAGE MODELS TO REDUCE COMPUTATIONAL RESOURCE CONSUMPTION
Publication number
US20260289108A1
Application number
19695513
Filed
Jun 2, 2026
Published
Sep 24, 2026
Inventors
12
Claims
20

Classified under

G06F 40/20 Physics & computing
Read the full filing (official PDF) ↗ Open in the Patent Tracker

More from Google in AI & software

Summaries are simplified from the filing’s own abstract and first claim. A patent filing is not a product announcement.
Patent data and drawings: U.S. Patent and Trademark Office (USPTO). Nebula is not affiliated with or endorsed by the USPTO.