1 citations · 1 across the 11 of their papers we have counts for
11 papers
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…
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…
EVA: Editing for Versatile Alignment against Jailbreaks
Yi Wang, Hongye Qiu, Yue Xu +4
Large Language Models (LLMs) and Vision Language Models (VLMs) have demonstrated impressive capabilities but remain vulnerable to jailbreaking attacks, where adversaries exploit te…
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…
Speculating LLMs' Chinese Training Data Pollution from Their Tokens
Qingjie Zhang, Di Wang, Haoting Qian +7
Tokens are basic elements in the datasets for LLM training. It is well-known that many tokens representing Chinese phrases in the vocabulary of GPT (4o/4o-mini/o1/o3/4.5/4.1/o4-min…
Understanding the Dilemma of Unlearning for Large Language Models
Qingjie Zhang, Haoting Qian, Zhicong Huang +5
Unlearning seeks to remove specific knowledge from large language models (LLMs), but its effectiveness remains contested. On one side, "forgotten" knowledge can often be recovered…
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…
Stop Before You Fail: Operational Capability Boundaries for Mitigating Unproductive Reasoning in Large Reasoning Models
Qingjie Zhang, Yujia Fu, Yang Wang +5
Current answering paradigms for Large Reasoning Models (LRMs) often fail to account for the fact that some questions may lie beyond the model's operational capability boundary, lea…
SafeSearch: Automated Red-Teaming of LLM-Based Search Agents
Jianshuo Dong, Sheng Guo, Hao Wang +6
Search agents connect LLMs to the Internet, enabling them to access broader and more up-to-date information. However, this also introduces a new threat surface: unreliable search r…
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…
Understanding the Dark Side of LLMs' Intrinsic Self-Correction
Qingjie Zhang, Di Wang, Haoting Qian +7
Intrinsic self-correction was proposed to improve LLMs' responses via feedback prompts solely based on their inherent capability. However, recent works show that LLMs' intrinsic se…