Profiles2024-2025
Zhangchen Xu
University of Washington
6Papers
0Last author
10Unique co-authors
2First author
0Solo
First and last author come from byline position, which some venues assign alphabetically.
Recent papers6
- SafeChain: Safety of Language Models with Long Chain-of-Thought Reasoning CapabilitiesAuthor 2 of 8ACL Findings 2025 · 15 citations
- KodCode: A Diverse, Challenging, and Verifiable Synthetic Dataset for CodingAuthor 1 of 6ACL Findings 2025 · 9 citations
- Small Models Struggle to Learn from Strong ReasonersAuthor 3 of 9ACL Findings 2025 · 5 citations
- ArtPrompt: ASCII Art-based Jailbreak Attacks against Aligned LLMsAuthor 2 of 8ACL 2024 · 36 citations
- ACE: A Model Poisoning Attack on Contribution Evaluation Methods in Federated LearningAuthor 1 of 6USENIX Security 2024 · 11 citations
- CleanGen: Mitigating Backdoor Attacks for Generation Tasks in Large Language ModelsAuthor 2 of 7EMNLP 2024 · 7 citations
