5 papers
Trajectory-Guided Forget-Recover Network for Continual LLM Unlearning
Zezheng Wu, Xinghe Cheng, Qinggang Zhang +4
Machine unlearning aims to eliminate the influence of sensitive data on a model. In the real world, unlearning requests arrive continually, which gives rise to two challenges. Firs…
U-CAN: Utility-Aware Contrastive Attenuation for Efficient Unlearning in Generative Recommendation
Zezheng Wu, Rui Wang, Xinghe Cheng +4
Generative Recommendation (GenRec) typically leverages Large Language Models (LLMs) to redefine personalization as an instruction-driven sequence generation task. However, fine-tun…
BamaER: A Behavior-Aware Memory-Augmented Model for Exercise Recommendation
Qing Yang, Yuhao Jiang, Rui Wang +6
Exercise recommendation focuses on personalized exercise selection conditioned on students' learning history, personal interests, and other individualized characteristics. Despite…
Cumulative Path-Level Semantic Reasoning for Inductive Knowledge Graph Completion
Jiapu Wang, Xinghe Cheng, Zezheng Wu +6
Conventional Knowledge Graph Completion (KGC) methods aim to infer missing information in incomplete Knowledge Graphs (KGs) by leveraging existing information, which struggle to pe…
A Large-Scale Chinese Knowledge Graph-Text Alignment Dataset for Benchmarking Knowledge-Grounded LLMs
Chengwei Wu, Jiapu Wang, Mingyang Gao +10
Reliable evaluation of knowledge-grounded Large Language Models (LLMs) in Chinese requires resources that explicitly align Chinese-language text with verifiable Knowledge Graph (KG…