10 papers
Exploring and Exploiting the Inherent Efficiency within Large Reasoning Models for Self-Guided Efficiency Enhancement
Weixiang Zhao, Jiahe Guo, Yang Deng +7
Recent advancements in large reasoning models (LRMs) have significantly enhanced language models' capabilities in complex problem-solving by emulating human-like deliberative think…
MPO: Multilingual Safety Alignment via Reward Gap Optimization
Weixiang Zhao, Yulin Hu, Yang Deng +8
Large language models (LLMs) have become increasingly central to AI applications worldwide, necessitating robust multilingual safety alignment to ensure secure deployment across di…
How Does Sequence Modeling Architecture Influence Base Capabilities of Pre-trained Language Models? Exploring Key Architecture Design Principles to Avoid Base Capabilities Degradation
Xin Lu, Yanyan Zhao, Si Wei +3
Pre-trained language models represented by the Transformer have been proven to possess strong base capabilities, and the representative self-attention mechanism in the Transformer…
Teaching Language Models to Evolve with Users: Dynamic Profile Modeling for Personalized Alignment
Weixiang Zhao, Xingyu Sui, Yulin Hu +6
Personalized alignment is essential for enabling large language models (LLMs) to engage effectively in user-centric dialogue. While recent prompt-based and offline optimization met…
When Less Language is More: Language-Reasoning Disentanglement Makes LLMs Better Multilingual Reasoners
Weixiang Zhao, Jiahe Guo, Yang Deng +9
Multilingual reasoning remains a significant challenge for large language models (LLMs), with performance disproportionately favoring high-resource languages. Drawing inspiration f…
AdaSteer: Your Aligned LLM is Inherently an Adaptive Jailbreak Defender
Weixiang Zhao, Jiahe Guo, Yulin Hu +8
Despite extensive efforts in safety alignment, large language models (LLMs) remain vulnerable to jailbreak attacks. Activation steering offers a training-free defense method but re…