Understand Galileo's Tone Metric

Definition: Classifies the tone of the response into 9 different emotion categories: neutral, joy, love, fear, surprise, sadness, anger, annoyance, and confusion.

Calculation: We leverage a Small Language Model (SLM) trained on open-source and internal datasets.

Our classifier's accuracy on the GoEmotions (open-source) dataset is about 80% for the validation set.

Usefulness: Recognize and categorize the emotional tone of responses to align with user preferences, allowing for optimization by discouraging undesirable tones and promoting preferred emotional responses.

Last updated