Google patents AI that adjusts answers based on your personal preferences
This filing describes a method for customizing AI responses by mapping user preferences to a specific point on a scale between two opposing traits, such as luxury versus budget. The system uses user inputs to determine this position and injects a corresponding signal into the AI model to steer the generated output toward the favored trait. It allows for real-time adjustment of the AI's behavior as the user interacts with it.
In the filing’s own words
Disclosure relates to controlling AI responses through preference-based activation steering. A prompt is received and associated with a preference represented as a specific position within a range between two opposing features associated with the preference (e.g., luxury vs. budget related to cost preference). This position, which indicates which feature is favored and by how much, is set via interactive user interface inputs across multiple modalities: direct selection of candidate preferences (select implementation), iterative calibration between model-generated responses (calibrate implementation), or learning from interactions (learn implementation). Based on the position determined from the input, a corresponding steering strength of the position is injected into the model's stream to influence response generation. This allows the AI to align its output with the favored features/attributes. The system enables dynamic adjustment of responses through multiple interactions, where each interaction updates the position to refine the personalization in real-time.
What exactly they claim (claim 1)
1. A computer-implemented method, comprising: identifying a preference associated with a prompt, wherein the preference is associated with a first feature and a second feature; determining, based on an input, a position within a range defined using the first feature and the second feature; providing the position within the range to a model to modify generation of a response to the prompt based on the position; receiving, from the model, the response to the prompt; and initiating display of the response.
Facts
- Company
- Google (GOOGLE LLC)
- Official title
- PERSONALIZING AI MODEL WITH PREFERENCE-BASED ACTIVATION STEERING
- Publication number
- US20260320141A1
- Application number
- 19643357
- Filed
- Apr 9, 2026
- Published
- Oct 15, 2026
- Inventors
- 6
- Claims
- 20
Classified under
G06F 16/9535 Physics & computingG06F 16/957 Physics & computingMore from Google in AI & software
- Google patents video search that answers questions using AI descriptions Sep 15, 2026
- Google patents photo tool that removes people and their gear Sep 15, 2026
- Google patents AI that writes live meeting notes and summaries Sep 15, 2026
- Google patents AI tool that turns messy emergency notes into clear messages Sep 3, 2026
- Google patents AI that clicks through apps to finish tasks for you Sep 24, 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.