AdaCLF: An Adaptive Curriculum Learning Framework for Emotional Support Conversation

Geng Tu, Taiyu Niu, Ruifeng Xu, Bin Liang, Erik Cambria

Abstract: Emotional support conversation (ESC) aims to alleviate emotional distress using data-driven approaches trained on human-generated responses. However, the subjective and open-ended nature of human conversations presents challenges in training ESC models due to uneven complexities in query–response pairs. This uneven complexity impedes the efficiency and effectiveness of learning in ESC models. Based on this, we propose an adaptive curriculum learning framework (AdaCLF) to dynamically choose courses of varying complexity according to the learning status of the ESC model. AdaCLF consists of two main components: the student model (referred to as the ESC model) and the teacher model (responsible for selecting appropriate data to enhance the student model’s training). The framework operates within the reinforcement learning paradigm, where the teacher model utilizes feedback from the student model to optimize its teaching strategy, fostering collaborative evolution. Both automatic and human evaluations on benchmark datasets demonstrate that our framework significantly improves existing ESC methods, generating more effective supportive responses.