7 papers
SafeNeuron: Neuron-Level Safety Alignment for Large Language Models
Zhaoxin Wang, Jiaming Liang, Fengbin Zhu +5
Large language models (LLMs) and multimodal LLMs are typically safety-aligned before release to prevent harmful content generation. However, recent studies show that safety behavio…
On Reasoning Strength Planning in Large Reasoning Models
Leheng Sheng, An Zhang, Zijian Wu +5
Recent studies empirically reveal that large reasoning models (LRMs) can automatically allocate more reasoning strengths (i.e., the number of reasoning tokens) for harder problems,…
AlphaSteer: Learning Refusal Steering with Principled Null-Space Constraint
Leheng Sheng, Changshuo Shen, Weixiang Zhao +6
As LLMs are increasingly deployed in real-world applications, ensuring their ability to refuse malicious prompts, especially jailbreak attacks, is essential for safe and reliable u…
Who Transfers Safety? Identifying and Targeting Cross-Lingual Shared Safety Neurons
Xianhui Zhang, Chengyu Xie, Linxia Zhu +6
Multilingual safety remains significantly imbalanced, leaving non-high-resource (NHR) languages vulnerable compared to robust high-resource (HR) ones. Moreover, the neural mechanis…
Understanding Multilingualism in Mixture-of-Experts LLMs: Routing Mechanism, Expert Specialization, and Layerwise Steering
Yuxin Chen, Zhengzhou Cai, Xiangtian Ji +4
Mixture-of-Experts (MoE) architectures have shown strong multilingual capabilities, yet the internal mechanisms underlying performance gains and cross-language differences remain i…
RSafe: Incentivizing proactive reasoning to build robust and adaptive LLM safeguards
Jingnan Zheng, Xiangtian Ji, Yijun Lu +6
Large Language Models (LLMs) continue to exhibit vulnerabilities despite deliberate safety alignment efforts, posing significant risks to users and society. To safeguard against th…