11 papers
Safety Anchor: Defending Harmful Fine-tuning via Geometric Bottlenecks
Guoxin Lu, Letian Sha, Qing Wang +4
The safety alignment of Large Language Models (LLMs) remains vulnerable to Harmful Fine-tuning (HFT). While existing defenses impose constraints on parameters, gradients, or intern…
PRISM: Personalized Recommendation via Information Synergy Module
Xinyi Zhang, Yutong Li, Peijie Sun +2
Multimodal sequential recommendation (MSR) leverages diverse item modalities to improve recommendation accuracy, while achieving effective and adaptive fusion remains challenging.…
Differentiated Directional Intervention A Framework for Evading LLM Safety Alignment
Peng Zhang, Peijie Sun
Safety alignment instills in Large Language Models (LLMs) a critical capacity to refuse malicious requests. Prior works have modeled this refusal mechanism as a single linear direc…
Speech Recognition Model Improves Text-to-Speech Synthesis using Fine-Grained Reward
Guansu Wang, Peijie Sun
Recent advances in text-to-speech (TTS) have enabled models to clone arbitrary unseen speakers and synthesize high-quality, natural-sounding speech. However, evaluation methods lag…
HADSF: Aspect Aware Semantic Control for Explainable Recommendation
Zheng Nie, Peijie Sun
Recent advances in large language models (LLMs) promise more effective information extraction for review-based recommender systems, yet current methods still (i) mine free-form rev…
A User-Centric Multi-Intent Benchmark for Evaluating Large Language Models
Jiayin Wang, Fengran Mo, Weizhi Ma +3
Large language models (LLMs) are essential tools that users employ across various scenarios, so evaluating their performance and guiding users in selecting the suitable service is…