collaborators

21 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

GameCraft-Bench: Can Agents Build Playable Games End-to-End in a Real Game Engine?

Tongxu Luo, Rongsheng Wang, Jiaxi Bi +22

Game generation is an emerging application of coding agents, requiring models to transform natural-language specifications into playable interactive systems. Unlike traditional cod…

cs.AI2026

From Risk Classification to Action Plan Remediation: A Guardrail Feedback Driven Framework for LLM Agents

Yuhao Sun, Jiacheng Zhang, Shaanan Cohney +3

LLM-based guardrails typically safeguard agents by evaluating proposed actions or inputs before execution, producing safety signals such as binary allow/deny decisions, risk catego…

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.LG2026

LASA: Language-Agnostic Semantic Alignment at the Semantic Bottleneck for LLM Safety

Junxiao Yang, Haoran Liu, Jinzhe Tu +9

Large language models (LLMs) often demonstrate strong safety performance in high-resource languages, yet exhibit severe vulnerabilities when queried in low-resource languages. We a…

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…