12 papers
DeRes: Decoupling Residual Stability and Adaptivity for Scalable CTR Prediction
Wenzhuo Cheng, Shipeng Nie, Qixin Guo +3
Transformer-based CTR models face a growing bottleneck at the residual connection: under Pre-Norm, early user-interest signals are diluted layer by layer; the identity skip cannot…
Aligned but Fragile: Enhancing LLM Safety Robustness via Zeroth-Order Optimization
Zhihao Liu, Yifan Wu, Jian Lou +3
Safety alignment for large language models (LLMs) aims to reduce harmful or unsafe behavior while preserving general utility. However, recent findings reveal that alignment effects…
Mitigating Many-shot Jailbreak Attacks with One Single Demonstration
Kejia Chen, Jiawen Zhang, Boheng Li +6
Many-shot jailbreaking (MSJ) causes safety-aligned language models to answer harmful queries by preceding them with many harmful question-answer demonstrations. We study why this a…
Confidence-Aware Alignment Makes Reasoning LLMs More Reliable
Kejia Chen, Jiawen Zhang, Yihong Wu +5
Large reasoning models often reach correct answers through flawed intermediate steps, creating a gap between final accuracy and reasoning reliability. Existing alignment strategies…
CapsID: Soft-Routed Variable-Length Semantic IDs for Generative Recommendation
Wenzhuo Cheng, Menghang Gong, Qixin Guo +4
Generative recommendation maps each item to a sequence of Semantic IDs (SIDs) and recasts retrieval as autoregressive token generation. In this paradigm the main bottleneck is the…
Understanding and Preserving Safety in Fine-Tuned LLMs
Jiawen Zhang, Yangfan Hu, Kejia Chen +7
Fine-tuning is an essential and pervasive functionality for applying large language models (LLMs) to downstream tasks. However, it has the potential to substantially degrade safety…