most citedWhen Smiley Turns Hostile: Interpreting How Emojis Trigger LLMs' Toxicity

1 citations · 1 across the 5 of their papers we have counts for

collaborators

6 papers

cs.CV2026

Video-KTR: Reinforcing Video Reasoning via Key Token Attribution

Ziyue Wang, Sheng Jin, Zhongrong Zuo +5

Reinforcement learning (RL) has shown strong potential for enhancing reasoning in multimodal large language models, yet existing video reasoning methods often rely on coarse sequen…

cs.CV2026

The Side Effects of Being Smart: Safety Risks in MLLMs' Multi-Image Reasoning

Renmiao Chen, Yida Lu, Shiyao Cui +6

As Multimodal Large Language Models (MLLMs) acquire stronger reasoning capabilities to handle complex, multi-image instructions, this advancement may pose new safety risks. We stud…

cs.CL20251 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

Exploring Multimodal Challenges in Toxic Chinese Detection: Taxonomy, Benchmark, and Findings

Shujian Yang, Shiyao Cui, Chuanrui Hu +5

Detecting toxic content using language models is important but challenging. While large language models (LLMs) have demonstrated strong performance in understanding Chinese, recent…

cs.MM2025

ShieldVLM: Safeguarding the Multimodal Implicit Toxicity via Deliberative Reasoning with LVLMs

Shiyao Cui, Qinglin Zhang, Xuan Ouyang +6

Toxicity detection in multimodal text-image content faces growing challenges, especially with multimodal implicit toxicity, where each modality appears benign on its own but convey…

cs.CL2025

Revisiting Backdoor Attacks on LLMs: A Stealthy and Practical Poisoning Framework via Harmless Inputs

Jiawei Kong, Hao Fang, Xiaochen Yang +5

Recent studies have widely investigated backdoor attacks on Large Language Models (LLMs) by inserting harmful question-answer (QA) pairs into their training data. However, we revis…