Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:
ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Home/Authors/Xianglin Yang

Xianglin Yang

2 indexed papers

Recent (6 mo)
2
With code
0
Influential cites
0
Benchmarked
0

Publications per year

2
26

Top categories

AI×2Crypto×2Software Eng.×1ML×1

Frequent co-authors

Jin Song Dong2×
Xiaoyue Lu1×
Haijun Liu1×
Jiahao Liu1×
Kuntai Cai1×
Yan Xiao1×

Research Timeline

2026
Inverting the Shield: Systematically Generating Safety Tests from Policy Specifications

The paper introduces POLARIS, a novel framework that systematically generates comprehensive and verifiable safety tests for LLMs by formalizing natural language policies into First-Order Logic and exploring the resulting Semantic Policy Graph.

Turning Bias into Bugs: Bandit-Guided Style Manipulation Attacks on LLM Judges

The paper introduces BITE, a black-box adversarial framework that exploits stylistic biases in LLM judges by adaptively generating semantically equivalent edits to artificially inflate assigned scores.

Highlighted terms show continued research focus across papers

Papers

cs.AIcs.CRcs.SERecentMay 24, 2026

Inverting the Shield: Systematically Generating Safety Tests from Policy Specifications

Xiaoyue Lu, Xianglin Yang, Haijun Liu, Jiahao Liu +3 more

The paper introduces POLARIS, a novel framework that systematically generates comprehensive and verifiable safety tests for LLMs by formalizing natural language policies into First-Order Logic and exp…

View →
cs.CRcs.AIcs.LGRecentMay 24, 2026

Turning Bias into Bugs: Bandit-Guided Style Manipulation Attacks on LLM Judges

Xianglin Yang, Bryan Hooi, Gelei Deng, Tianwei Zhang +1 more

The paper introduces BITE, a black-box adversarial framework that exploits stylistic biases in LLM judges by adaptively generating semantically equivalent edits to artificially inflate assigned scores…

View →