Daqiang Zhang

Jiaheng Zhang, Daqiang Zhang

The integration of Large Language Models (LLMs) into explainable recommendation systems often leads to a performance-efficiency trade-off in end-to-end architectures, where joint optimization of ranking and explanation can result in suboptimal compromises. To resolve this, we propose Prism, a novel decoupled framework that rigorously separates the recommendation process into a dedicated ranking stage and an explanation generation stage. Inspired by knowledge distillation, Prism leverages a powerful teacher LLM (e.g., FLAN-T5-XXL) as an Oracle to produce high-fidelity explanatory knowledge. A compact, fine-tuned student model (e.g., BART-Base), the Prism, then specializes in synthesizing this knowledge into personalized explanations. This decomposition ensures that each component is optimized for its specific objective, eliminating inherent conflicts in coupled models. Extensive experiments on benchmark datasets demonstrate that our 140M-parameter Prism model significantly outperforms its 11B-parameter teacher in human evaluations of faithfulness and personalization, while achieving a 24 times speedup and a 10 times reduction in memory consumption during inference. These results validate that decoupling, coupled with targeted distillation, provides an efficient and effective pathway to high-quality explainable recommendation.

Daqiang Zhang, Qin Zou, Haoyi Xiong

The Internet of Things (IoT) aims at interconnecting everyday objects (including both things and users) and then using this connection information to provide customized user services. However, IoT does not work in its initial stages without adequate acquisition of user preferences. This is caused by cold-start problem that is a situation where only few users are interconnected. To this end, we propose CRUC scheme - Cold-start Recommendations Using Collaborative Filtering in IoT, involving formulation, filtering and prediction steps. Extensive experiments over real cases and simulation have been performed to evaluate the performance of CRUC scheme. Experimental results show that CRUC efficiently solves the cold-start problem in IoT.

Daqiang Zhang, Rongbo Zhu, Shuqiqiu Men et al.

Extensive research has been conducted on query log analysis. A query log is generally represented as a bipartite graph on a query set and a URL set. Most of the traditional methods used the raw click frequency to weigh the link between a query and a URL on the click graph. In order to address the disadvantages of raw click frequency, researchers proposed the entropy-biased model, which incorporates raw click frequency with inverse query frequency of the URL as the weighting scheme for query representation. In this paper, we observe that the inverse query frequency can be considered a global property of the URL on the click graph, which is more informative than raw click frequency, which can be considered a local property of the URL. Based on this insight, we develop the global consistency model for query representation, which utilizes the click frequency and the inverse query frequency of a URL in a consistent manner. Furthermore, we propose a new scheme called inverse URL frequency as an effective way to capture the global property of a URL. Experiments have been conducted on the AOL search engine log data. The result shows that our global consistency model achieved better performance than the current models.