Guardrail machine learning model for automated software
US12259952B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Apr 17, 2024 |
| Grant date | Mar 25, 2025 |
| Priority date | — |
| Expiry date | Apr 17, 2044 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06N20/00
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
In one aspect, a method of guarding an automated software includes generating, by a first language model, a training set of rule-violating data, generating, by the first language model, a training set of contrastive examples by altering the rule-violating data into non-violating data, training a guardrail machine learning model using the generated training sets, generating, with an automated software, an output based on a user input, monitoring with the trained guardrail machine learn model whether the generated output violates a rule, and preventing the automated software from transmitting to the user the generated output that violates a rule.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.