Nvidia patents method for tailoring AI chat responses to user preferences
Nvidia describes a system that uses multiple AI models to evaluate different aspects of a user's request, creating a personalized profile. This profile guides a main language model to generate responses that better match the user's specific needs and style. The system improves itself by comparing the generated answer to the original request and adjusting its internal settings.
In the filing’s own words
Disclosed are systems and techniques for training personalized language models. The techniques include applying a plurality of first machine learning models to a first input prompt. Each of the plurality of first machine learning models generates a respective reward value of a first plurality of reward values. The techniques include applying a second machine learning model to the first plurality of reward values to obtain first reward value embeddings; applying a third machine learning model to the first reward value embeddings and the first input prompt to obtain a first output response; calculating a first loss based on a comparison between the first output response and the first input prompt; and causing the second machine learning model to be modified based on the first loss.
What exactly they claim (claim 1)
1. A method comprising: applying a plurality of first machine learning models to a first input prompt, wherein individual first machine learning models of the plurality of first machine learning models comprise a layer that generates a respective reward value of a first plurality of reward values for a respective attribute of a plurality of attributes; applying a second machine learning model to the first plurality of reward values to obtain first encoded reward values comprising vector embeddings, wherein the first encoded reward values are combined with an input of a language machine learning model to condition the language machine learning model to generate a first output response aligned with the plurality of attributes; applying the language machine learning model to the first encoded reward values and the first input prompt to obtain the first output response; calculating a first loss based at least on a comparison between the first output response and the first input prompt; and updating one or more parameters of the second machine learning model based at least on the first loss.
Facts
- Company
- Nvidia (NVIDIA Corporation)
- Official title
- Personalized language models for conversational AI systems and applications
- Patent number
- US12758878B2
- Application number
- 18351900
- Filed
- Jul 13, 2023
- Granted
- Oct 13, 2026
- Inventors
- 2
- Claims
- 21
Classified under
A63F 13/67 Human necessitiesG06F 40/284 Physics & computingG06F 40/40 Physics & computingG06N 20/00 Physics & computingG06F 40/35 Physics & computingMore from Nvidia in AI & software
- Nvidia patents AI coach that analyzes your gameplay to suggest strategies Oct 13, 2026
- Nvidia patents AI system that writes and voices character conversations Sep 10, 2026
- Nvidia patents system that uses AI to find bugs in game videos Sep 17, 2026
- Nvidia patents AI method to make digital characters move realistically Sep 8, 2026
- Nvidia patents AI system that builds image generators from text prompts Sep 15, 2026
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.