3 papers
cs.CL2025
Foot-In-The-Door: A Multi-turn Jailbreak for LLMs
Zixuan Weng, Xiaolong Jin, Jinyuan Jia +1
Ensuring AI safety is crucial as large language models become increasingly integrated into real-world applications. A key challenge is jailbreak, where adversarial prompts bypass b…
cs.AI2024
Conditional LoRA Parameter Generation
Xiaolong Jin, Kai Wang, Dongwen Tang +4
Generative models have achieved remarkable success in image, video, and text domains. Inspired by this, researchers have explored utilizing generative models to generate neural net…
cs.LG2024
Look Globally and Reason: Two-stage Path Reasoning over Sparse Knowledge Graphs
Saiping Guan, Jiyao Wei, Xiaolong Jin +2
Sparse Knowledge Graphs (KGs), frequently encountered in real-world applications, contain fewer facts in the form of (head entity, relation, tail entity) compared to more populated…