6 citations · 23 across the 11 of their papers we have counts for
5 papers · 1 filter
Jailbreak Large Vision-Language Models Through Multi-Modal Linkage
Yu Wang, Xiaofei Zhou, Yichen Wang +2
With the significant advancement of Large Vision-Language Models (VLMs), concerns about their potential misuse and abuse have grown rapidly. Previous studies have highlighted VLMs'…
Can LLM Graph Reasoning Generalize beyond Pattern Memorization?
Yizhuo Zhang, Heng Wang, Shangbin Feng +4
Large language models (LLMs) demonstrate great potential for problems with implicit graphical structures, while recent works seek to enhance the graph reasoning capabilities of LLM…
Learning Syntax Without Planting Trees: Understanding Hierarchical Generalization in Transformers
Kabir Ahuja, Vidhisha Balachandran, Madhur Panwar +4
Transformers trained on natural language data have been shown to learn its hierarchical structure and generalize to sentences with unseen syntactic structures without explicitly en…
Stumbling Blocks: Stress Testing the Robustness of Machine-Generated Text Detectors Under Attacks
Yichen Wang, Shangbin Feng, Abe Bohan Hou +5
The widespread use of large language models (LLMs) is increasing the demand for methods that detect machine-generated text to prevent misuse. The goal of our study is to stress tes…
k-SemStamp: A Clustering-Based Semantic Watermark for Detection of Machine-Generated Text
Abe Bohan Hou, Jingyu Zhang, Yichen Wang +2
Recent watermarked generation algorithms inject detectable signatures during language generation to facilitate post-hoc detection. While token-level watermarks are vulnerable to pa…