31 October 2024
The paper, entitled 'Towards Empathetic Conversational Recommender Systems' presents an empathetic conversational recommendation framework. To generate human-like emotional responses, the framework applies retrieval-augmented prompts to fine-tune a pre-trained language model to align with emotions and mitigate hallucination.
Paper details: Xiaoyu Zhang (Shandong University), Ruobing Xie (Tencent), Yougang Lyu (Shandong University and University of Amsterdam), Xin Xin (Shandong University), Pengjie Ren (Shandong University), Mingfei Liang (Tencent), Bo Zhang (Tencent), Zhanhui Kang (Tencent), Maarten de Rijke (University of Amsterdam), and Zhaochun Ren (Leiden University). Towards Empathetic Conversational Recommender Systems. Link: https://irlab.science.uva.nl/wp-content/papercite-data/pdf/zhang-2024-towards.pdf