Patent Leaderboard
USPTO Patent Rankings Data through Dec 31, 2025
Home › Calibrating confidence scores of a machine learning model trained as a natural language interface

Calibrating confidence scores of a machine learning model trained as a natural language interface

US Patent 12430330 · Granted Sep 30, 2025

Assignee

Inventors

View full patent text on Google Patents →

More Patents by These Inventors

Enhanced logits for natural language processing2025
Enhanced logits for natural language processing2025
Enhanced logits for natural language processing2025
Fine-tuning multi-head network from a single transformer layer of pre-trained la2025
Fine-tuning multi-head network from a single transformer layer of pre-trained la2025
Using a generative adversarial network to train a semantic parser of a dialog sy2025
Model robustness on operators and triggering keywords in natural language to a m2025
Model robustness on operators and triggering keywords in natural language to a m2025
Model robustness on operators and triggering keywords in natural language to a m2025
Model robustness on operators and triggering keywords in natural language to a m2025
Model robustness on operators and triggering keywords in natural language to a m2025
Model robustness on operators and triggering keywords in natural language to a m2025