23 papers
Towards Understanding Continual Factual Knowledge Acquisition of Language Models: From Theory to Algorithm
Haoyu Wang, Yifan Shang, Zhongxiang Sun +3
Continual Pre-Training (CPT) is essential for enabling Language Models (LMs) to integrate new knowledge without erasing old. While classical CPT techniques like data replay have be…
GenRecEdit: Adapting Model Editing for Generative Recommendation with Cold-Start Items
Chenglei Shen, Teng Shi, Weijie Yu +2
Generative recommendation (GR) has shown strong potential for sequential recommendation in an end-to-end generation paradigm. However, existing GR models suffer from severe cold-st…
Hidden States Know Where Reasoning Diverges: Credit Assignment via Span-Level Wasserstein Distance
Xinzhu Chen, Wei He, Huichuan Fan +7
Group Relative Policy Optimization (GRPO) performs coarse-grained credit assignment in reinforcement learning with verifiable rewards (RLVR) by assigning the same advantage to all…
Enhancing Bandit Algorithms with LLMs for Time-varying User Preferences in Streaming Recommendations
Chenglei Shen, Yi Zhan, Weijie Yu +2
In real-world streaming recommender systems, user preferences evolve dynamically over time. Existing bandit-based methods treat time merely as a timestamp, neglecting its explicit…
Deep Search with Hierarchical Meta-Cognitive Monitoring Inspired by Cognitive Neuroscience
Zhongxiang Sun, Qipeng Wang, Weijie Yu +3
Deep search agents powered by large language models have demonstrated strong capabilities in multi-step retrieval, reasoning, and long-horizon task execution. However, their practi…
When Personalization Misleads: Understanding and Mitigating Hallucinations in Personalized LLMs
Zhongxiang Sun, Yi Zhan, Chenglei Shen +4
Personalized large language models (LLMs) adapt model behavior to individual users to enhance user satisfaction, yet personalization can inadvertently distort factual reasoning. We…