8 papers
Mitigating Scaffolding Collapse in Socratic Tutors via Representation Alignment
Jing Shao, Qifeng Wu, Hanyu Zhang +2
Large language model (LLM)-based Socratic tutors increasingly guide students through multi-turn questioning, but they can suffer from scaffolding collapse: under sustained student…
Learning to Conceal Risk: Controllable Multi-turn Red Teaming for LLMs in the Financial Domain
Gang Cheng, Haibo Jin, Wenbin Zhang +2
Large Language Models (LLMs) are increasingly deployed in finance, where unsafe behavior can lead to serious regulatory risks. However, most red-teaming research focuses on overtly…
Now You Hear Me: Audio Narrative Attacks Against Large Audio-Language Models
Ye Yu, Haibo Jin, Yaoning Yu +2
Large audio-language models increasingly operate on raw speech inputs, enabling more seamless integration across domains such as voice assistants, education, and clinical triage. T…
JailbreakZoo: Survey, Landscapes, and Horizons in Jailbreaking Large Language and Vision-Language Models
Haibo Jin, Leyang Hu, Xinnuo Li +4
The rapid evolution of artificial intelligence (AI) through developments in Large Language Models (LLMs) and Vision-Language Models (VLMs) has brought significant advancements acro…
Exploring the Vulnerability of the Content Moderation Guardrail in Large Language Models via Intent Manipulation
Jun Zhuang, Haibo Jin, Ye Zhang +4
Intent detection, a core component of natural language understanding, has considerably evolved as a crucial mechanism in safeguarding large language models (LLMs). While prior work…
InfoFlood: Jailbreaking Large Language Models with Information Overload
Advait Yadav, Haibo Jin, Man Luo +2
Large Language Models (LLMs) have demonstrated remarkable capabilities across various domains. However, their potential to generate harmful responses has raised significant societa…