7 papers
Causal-HalBench: Uncovering LVLMs Object Hallucinations Through Causal Intervention
Zhe Xu, Zhicai Wang, Junkang Wu +2
Large Vision-Language Models (LVLMs) often suffer from object hallucination, making erroneous judgments about the presence of objects in images. We propose this primar- ily stems f…
Robust Preference Optimization via Dynamic Target Margins
Jie Sun, Junkang Wu, Jiancan Wu +5
The alignment of Large Language Models (LLMs) is crucial for ensuring their safety and reliability in practical applications. Direct Preference Optimization (DPO) has emerged as an…
bi-GRPO: Bidirectional Optimization for Jailbreak Backdoor Injection on LLMs
Wence Ji, Jiancan Wu, Aiying Li +5
With the rapid advancement of large language models (LLMs), their robustness against adversarial manipulations, particularly jailbreak backdoor attacks, has become critically impor…
On Negative-aware Preference Optimization for Recommendation
Chenlu Ding, Daoxuan Liu, Jiancan Wu +6
Recommendation systems leverage user interaction data to suggest relevant items while filtering out irrelevant (negative) ones. The rise of large language models (LLMs) has garnere…
AdaViP: Aligning Multi-modal LLMs via Adaptive Vision-enhanced Preference Optimization
Jinda Lu, Jinghan Li, Yuan Gao +4
Preference alignment through Direct Preference Optimization (DPO) has demonstrated significant effectiveness in aligning multimodal large language models (MLLMs) with human prefere…
Aligning Multimodal LLM with Human Preference: A Survey
Tao Yu, Yi-Fan Zhang, Chaoyou Fu +14
Large language models (LLMs) can handle a wide variety of general tasks with simple prompts, without the need for task-specific training. Multimodal Large Language Models (MLLMs),…