activity
20242026
most citedAgent-SafetyBench: Evaluating the Safety of LLM Agents

3 citations · 11 across the 20 of their papers we have counts for

collaborators
Showing cs.CLShow all

11 papers · 1 filter

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.CL2026

The Missing Half: Unveiling Training-time Implicit Safety Risks Beyond Deployment

Zhexin Zhang, Yida Lu, Junfeng Fang +8

Safety risks of AI models have been widely studied at deployment time, such as jailbreak attacks that elicit harmful outputs. In contrast, safety risks emerging during training rem…

cs.CL2025★ 1 cited

"Give a Positive Review Only": An Early Investigation Into In-Paper Prompt Injection Attacks and Defenses for AI Reviewers

Qin Zhou, Zhexin Zhang, Zhi Li +1

With the rapid advancement of AI models, their deployment across diverse tasks has become increasingly widespread. A notable emerging application is leveraging AI models to assist…

cs.CL2025★ 1 cited

When Smiley Turns Hostile: Interpreting How Emojis Trigger LLMs' Toxicity

Shiyao Cui, Xijia Feng, Yingkang Wang +6

Emojis are globally used non-verbal cues in digital communication, and extensive research has examined how large language models (LLMs) understand and utilize emojis across context…

cs.CL2025

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…