Out-of-distribution query detection for improving language model generation
AssigneeIntuit Inc.
InventorsJiaxin ZHANG, Wendi CUI, Kamalika DAS, Sricharan KALLUR PALLI KUMAR
Life of this patent
Estimating the term…
Loading patent…
AssigneeIntuit Inc.
InventorsJiaxin ZHANG, Wendi CUI, Kamalika DAS, Sricharan KALLUR PALLI KUMAR
Estimating the term…
A method includes receiving a query from a user device and applying an embedding model to the query to generate a query vector data structure. A vector comparator is applied to the query vector data structure and embedded document chunk vector data structures to output a score measuring a semantic similarity between the vector data structures. The embedded document chunk vector data structures are generated by the embedding model being applied to documents in a knowledge base corpus. Responsive to the score failing to satisfy a threshold value, the query is rejected as being an out-of-distribution query by transmitting an electronic reject message. Responsive to the score satisfying the threshold value and indicating that the query is an in-distribution query, the language model is applied to the query and to the knowledge base corpus to output an answer. The method also includes returning the answer to the user device.
A method comprising:
(canceled)
(canceled)
(canceled)
A system comprising:
(canceled)
(canceled)
(canceled)
Dependencies are inferred from the claim text.