Hefei Xu

2026

doi dblp
AlignCP: Noise-Aware Preference Alignment for LLMs via Confidence and Polarity Reweighting.
Chen Cheng|Hefei Xu|Le Wu
Proceedings of the ACM Web Conference 2026, WWW 2026, Dubai, United Arab Emirates, originally scheduled for April 13-17, 2026, rescheduled for June 29 - July 3, 2026.
doi dblp
Mitigating Fine-tuning Bias: A Parameter-Efficient Debiasing Framework for Large Language Models.
Qiuyu Li|Kun Zhang|Le Wu|Hao Liu|Hefei Xu|Xin Li|Si Wei
Proceedings of the ACM Web Conference 2026, WWW 2026, Dubai, United Arab Emirates, originally scheduled for April 13-17, 2026, rescheduled for June 29 - July 3, 2026.
doi dblp
VC-Soup: Value-Consistency Guided Multi-Value Alignment for Large Language Models.
Hefei Xu|Le Wu|Yu Wang|Min Hou|Han Wu|Zhen Zhang|Meng Wang
Proceedings of the ACM Web Conference 2026, WWW 2026, Dubai, United Arab Emirates, originally scheduled for April 13-17, 2026, rescheduled for June 29 - July 3, 2026.

2025

doi dblp
Mitigating Distribution Shifts in Sequential Recommendation: An Invariance Perspective.
Yuxin Liao|Yonghui Yang|Min Hou|Le Wu|Hefei Xu|Hao Liu
Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2025, Padua, Italy, July 13-18, 2025
doi dblp
Fair Personalized Learner Modeling Without Sensitive Attributes.
Hefei Xu|Min Hou|Le Wu|Fei Liu|Yonghui Yang|Haoyue Bai|Richang Hong|Meng Wang
Proceedings of the ACM on Web Conference 2025, WWW 2025, Sydney, NSW, Australia, 28 April 2025- 2 May 2025