Zhao, Chengshuai
- Is Chain-of-Thought Reasoning of LLMs a Mirage? A Data Distribution Lens
2025/08/02 by Chengshuai Zhao, Zhen Tan, Zhao, Chengshuai +13 · 35 voices · 20 citations
#cs.AI #cs.CL #cs.LG
- From Generation to Judgment: Opportunities and Challenges of LLM-as-a-judge
2024/11/25 by Li, Dawei, Jiang, Bohan, Huang, Liangjie +10 · 2 voices · 115 citations
#Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #FOS: Computer and information sciences
- "Glue pizza and eat rocks" -- Exploiting Vulnerabilities in Retrieval-Augmented Generative Models
2024/06/26 by Tan, Zhen, Zhao, Chengshuai, Moraffah, Raha +5 · 12 citations
#Artificial Intelligence (cs.AI) #Cryptography and Security (cs.CR) #FOS: Computer and information sciences
- The Wolf Within: Covert Injection of Malice into MLLM Societies via an MLLM Operative
2024/02/20 by Tan, Zhen, Zhao, Chengshuai, Moraffah, Raha +4 · 1 citation
#Artificial Intelligence (cs.AI) #Computers and Society (cs.CY) #Cryptography and Security (cs.CR) #FOS: Computer and information sciences #Machine Learning (cs.LG)
- Ontology-Aware RAG for Improved Question-Answering in Cybersecurity Education
2024/12/10 by Zhao, Chengshuai, Agrawal, Garima, Zhang, Fan +5 · 2 citations
#Artificial Intelligence (cs.AI) #Computers and Society (cs.CY) #FOS: Computer and information sciences
- Catching Chameleons: Detecting Evolving Disinformation Generated using Large Language Models
2024/06/26 by Bohan Jiang, Chengshuai Zhao, Jiang, Bohan +5 · 1 citation
Social Sciences · #Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #FOS: Computer and information sciences #Misinformation and Its Impacts
- Causality Guided Representation Learning for Cross-Style Hate Speech Detection
2025/10/09 by Chengshuai Zhao, Zhao, Chengshuai, Shu Wan +9 · 1 citation
Computer Science · Psychology · #Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #Emotion and Mood Recognition #FOS: Computer and information sciences #Hate Speech and Cyberbullying Detection #Machine Learning (cs.LG) #Spam and Phishing Detection