Disambiguity in large language models
US12038918B1 · kind B1 · utility
Assignee
Inventors
Key dates
| Filing date | Jul 21, 2023 |
| Grant date | Jul 16, 2024 |
| Priority date | — |
| Expiry date | Jul 21, 2043 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06N3/084
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
Disambiguity in large language models (LLMs) includes receiving an original query in a user interface, generating an ambiguity query from the original query, and sending, via an application programming interface (API) of an LLM, the ambiguity query to the LLM. The ambiguity query includes the original query and training the LLM to recognize ambiguities. The method further includes receiving, via the API and responsive to the ambiguity query, a binary response and detecting, based at least in part on the binary response, the original query as ambiguous. Disambiguity may include detecting an ambiguity location in the original query using perturbed queries and the LLM.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.