ProUtt: Revolutionizing Human-Machine Dialogue with LLM-Powered Next Utterance Prediction

This research introduces ProUtt, a groundbreaking method for proactively predicting user utterances in human-machine dialogue! By leveraging LLMs to synthesize preference data, ProUtt promises to make interactions smoother and more intuitive, paving the way for significantly improved user experiences.

• •ProUtt utilizes LLMs to create a novel preference data synthesis method.
• •The method models intent reasoning to accurately predict user's next utterance.
• •Evaluations show promising results, enhancing human-machine dialogue.