2 papers
cs.LG2025
Reward-Driven Interaction: Enhancing Proactive Dialogue Agents through User Satisfaction Prediction
Wei Shen, Xiaonan He, Chuheng Zhang +3
Reward-driven proactive dialogue agents require precise estimation of user satisfaction as an intrinsic reward signal to determine optimal interaction strategies. Specifically, thi…
cs.CL2024
Leveraging Web-Crawled Data for High-Quality Fine-Tuning
Jing Zhou, Chenglin Jiang, Wei Shen +2
Most large language models are fine-tuned using either expensive human-annotated data or GPT-4 generated data which cannot guarantee performance in certain domains. We argue that a…