Author

Shaoyang Xu

3 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#artificial intelligence Jun 2026

Safety Paradox: How Enhanced Safety Awareness Leaves LLMs Vulnerable to Posterior Attack

This work formalizes the Safety Paradox, analytically showing that monotonic improvements in safety alignment naturally amplify posterior vulnerability, and establishes a causal link via reinforcement learning interventions, exemplifying that artificially degrading a model's safety judgment immunizes it against the att...

Ho-Ang P. Long, H. V. Le, Shaoyang Xu et al. · arXiv.org · 0 citations

#natural language process... Review Sep 2026

Aligned but Flattened: Analyzing the Trade-off between Cultural Alignment and Diversity in LLMs

This work proposes a synergistic evaluation framework that jointly formalizes cultural alignment and diversity and exposes the limitations of current post-training paradigms and calls for a shift toward alignment objectives that preserve cross-cultural pluralism.

Jingsheng Zhang, Shaoyang Xu, Wen-Xuan Zhang · 0 citations

#natural language process... Review Jun 2026

Beyond Alignment: Value Diversity as a Collective Property in Multicultural Agent Systems

Multicultural multi-agent systems are increasingly deployed in globally diverse settings, where different agents are grounded in different cultural backgrounds. Existing cultural evaluation focuses on value alignment: how closely a single agent matches a target culture. Yet alignment is a per-agent property and cannot...

Shaoyang Xu, Jingsheng Zhang, Ho-Ang P. Long et al. · arXiv.org · 0 citations