Showing cs.LGShow all
3 papers · 1 filter
cs.LG2026
LASA: Language-Agnostic Semantic Alignment at the Semantic Bottleneck for LLM Safety
Junxiao Yang, Haoran Liu, Jinzhe Tu +9
Large language models (LLMs) often demonstrate strong safety performance in high-resource languages, yet exhibit severe vulnerabilities when queried in low-resource languages. We a…
cs.LG2025
Loong: Synthesize Long Chain-of-Thoughts at Scale through Verifiers
Xingyue Huang, Rishabh, Gregor Franke +43
Recent advances in Large Language Models (LLMs) have shown that their reasoning capabilities can be significantly improved through Reinforcement Learning with Verifiable Reward (RL…
cs.LG2025
Guiding not Forcing: Enhancing the Transferability of Jailbreaking Attacks on LLMs via Removing Superfluous Constraints
Junxiao Yang, Zhexin Zhang, Shiyao Cui +2
Jailbreaking attacks can effectively induce unsafe behaviors in Large Language Models (LLMs); however, the transferability of these attacks across different models remains limited.…