Supervised Fine-tuning (SFT) and preference optimization (PO) are key methods for enhancing language models and aligning them with human preferences. However, scaling preference datasets for PO training is challenging, leading AI customer support systems to rely on SFT. To address this, we propose the Sentiment-guided Automatic Generation of Preference Datasets (Sentimatic) methodology to automatically generate customer preference datasets without human intervention using a publicly available dataset constructed for SFT. Our approach classifies responses by sentiment, fine-tunes models on them, and applies advanced sampling and evaluation techniques to ensure diversity and quality. Ultimately, we generated 1,174 customer preference datasets based on 357 test datasets, and through experiments, we confirmed that the AI customer support system trained on these datasets is capable of carefully considering customer emotions and generating professional and appropriate responses.

Effective emotional support in conversation requires strategic decision making, as it involves complex, context-sensitive reasoning tailored to diverse individual needs. The Emotional Support Conversation framework addresses this by organizing interactions into three distinct phases—exploration, comforting, and action—which guide strategy selection during response generation. While multitask learning has been applied to jointly optimize strategy prediction and response generation, it often suffers from task interference due to conflicting learning objectives. To overcome this, we propose the Strategy-Aware Refinement Module (STAR), which disentangles the decoder’s hidden states for each task and selectively fuses them via a dynamic gating mechanism. This design preserves task-specific representations while allowing controlled information exchange between tasks, thus reducing interference. Experimental results demonstrate that STAR effectively reduces task interference and achieves state-of-the-art performance in both strategy prediction and supportive response generation.