Salesforce, inc. (20250111155). SYSTEMS AND METHODS FOR TEXT GENERATION WITH VOCABULARY DETOXIFICATION
SYSTEMS AND METHODS FOR TEXT GENERATION WITH VOCABULARY DETOXIFICATION
Organization Name
Inventor(s)
Yingbo Zhou of Palo Alto CA US
Silvio Savarese of Palo Alto CA US
Semih Yavuz of Redwood City CA US
Caiming Xiong of Menlo Park CA US
SYSTEMS AND METHODS FOR TEXT GENERATION WITH VOCABULARY DETOXIFICATION
This abstract first appeared for US patent application 20250111155 titled 'SYSTEMS AND METHODS FOR TEXT GENERATION WITH VOCABULARY DETOXIFICATION
Original Abstract Submitted
embodiments described herein provide a method for mitigating toxic content in text generation by a neural network based framework. the method includes the following operations. a text input of a sequence of tokens is received via a communication interface. a first output probability for a next token generating is generated by a first neural network model that is trained to generate tokens belonging to a prioritized category of vocabulary, in response to the text input. a second output probability of the next token is generated by a second neural network model that is trained to generate tokens belonging to an indiscriminate vocabulary, in response to the text input. the next token for a text output based on a combined output probability computed based on a correction item reflective of the first output probability and the second output probability is generated in response to the text input.