activity
20242026
collaborators

22 papers

cs.CL2026

New Terms, New Toxicity: Consensus-based Chinese Neologism Toxicity Detection via Search-Augmented LLMs

Shiyao Cui, QingLin Zhang, Di Wang +7

Neologisms, emerging terms in meaning or form, can serve as new vehicles for toxic expression, like "country girl" as a stigmatizing label targeting feminism. Such toxic neologisms…

cs.CL2026

Safe Alone, Unsafe Together: Safeguarding Against Implicit Toxicity When Benign Images Combine

Jiaxian Lv, Shiyao Cui, Yingkang Wang +3

Multi-image content has become an increasingly prevalent form of visual communication in social media, giving rise to a new safety issue, multi-image implicit toxicity (MIIT), wher…

cs.LG2026

RUBAS: Rubric-Based Reinforcement Learning for Agent Safety

Xian Qi Loye, Qinglin Su, Zhexin Zhang +5

The evolution of LLMs into tool-enabled agents creates a new class of safety challenges associated with real-world execution rather than simple text generation. Existing alignment…

cs.CV2026

SynCred-Bench: Benchmarking Synthetic Credibility in AI-Generated Visual Misinformation

Junxiao Yang, Minghao Zhang, Xiaoce Wang +4

Recent generative models can now produce visual artifacts with realistic embedded text and layouts, creating a new misinformation threat: synthetic credibility. We introduce SYNCRE…

cs.CL2026

How Should We Enhance the Safety of Large Reasoning Models: An Empirical Study

Zhexin Zhang, Xian Qi Loye, Victor Shea-Jay Huang +8

Large Reasoning Models (LRMs) have achieved remarkable success on reasoning-intensive tasks such as mathematics and programming. However, their enhanced reasoning capabilities do n…

cs.CL2026

Be Careful When Fine-tuning On Open-Source LLMs: Your Fine-tuning Data Could Be Secretly Stolen!

Zhexin Zhang, Yuhao Sun, Junxiao Yang +4

Fine-tuning on open-source Large Language Models (LLMs) with proprietary data is now a standard practice for downstream developers to obtain task-specific LLMs. Surprisingly, we re…