10 papers
Probing Cultural Awareness in LLMs: A Case Study of Cross-Culture Aesthetic Stylistics
Jiashuo Wang, Fenggang Yu, Jian Wang +6
Large Language Models (LLMs) are increasingly deployed in diverse cultural contexts, yet their ability to master aesthetic stylistics, i.e., the strategic use of language to evoke…
Finding RELIEF: Shaping Reasoning Behavior without Reasoning Supervision via Belief Engineering
Chak Tou Leong, Dingwei Chen, Heming Xia +4
Large reasoning models (LRMs) have achieved remarkable success in complex problem-solving, yet they often suffer from computational redundancy or reasoning unfaithfulness. Current…
Refusal Falls off a Cliff: How Safety Alignment Fails in Reasoning?
Qingyu Yin, Chak Tou Leong, Linyi Yang +7
Large reasoning models (LRMs) with multi-step reasoning capabilities have shown remarkable problem-solving abilities, yet they exhibit concerning safety vulnerabilities that remain…
Constrain Alignment with Sparse Autoencoders
Qingyu Yin, Chak Tou Leong, Minjun Zhu +7
The alignment of large language models (LLMs) with human preferences remains a key challenge. While post-training techniques like Reinforcement Learning from Human Feedback (RLHF)…
Scaling over Scaling: Exploring Test-Time Scaling Plateau in Large Reasoning Models
Jian Wang, Boyan Zhu, Chak Tou Leong +2
Large reasoning models (LRMs) have exhibited the capacity of enhancing reasoning performance via internal test-time scaling. Building upon this, a promising direction is to further…
Why Safeguarded Ships Run Aground? Aligned Large Language Models' Safety Mechanisms Tend to Be Anchored in The Template Region
Chak Tou Leong, Qingyu Yin, Jian Wang +1
The safety alignment of large language models (LLMs) remains vulnerable, as their initial behavior can be easily jailbroken by even relatively simple attacks. Since infilling a fix…