PPaperPicks

Zhangchen Xu

13 papers at tracked venues · 9 at CORE A* · active 2024–2026

DBLP profile ↗ORCID search ↗

Venues

ACL ×6AsiaCCS ×2AAAI ×1EMNLP ×1ICLR ×1NAACL ×1USENIX Security ×1

Frequent coauthors

Radha Poovendran
×13
Fengqing Jiang
×12
Luyao Niu
×12
Bill Yuchen Lin
×7
Yuetai Li
×4
Bhaskar Ramasubramanian
×4
Bo Li
×4
Jinyuan Jia
×4
Xiang Yue
×2
Zhen Xiang
×2
Yang Liu
×1
Yueqin Yin
×1

Papers

  1. Temporal Sampling for Forgotten Reasoning in LLMs
    ACL 2026 ·
    Yuetai Li
    , Zhangchen Xu,
    Fengqing Jiang
    ,
    Bhaskar Ramasubramanian
    ,
    Luyao Niu
    ,
    Bill Yuchen Lin
    ,
    Xiang Yue
    ,
    Radha Poovendran
  2. ChatBug: A Common Vulnerability of Aligned LLMs Induced by Chat Templates
    AAAI 2025 ·
    Fengqing Jiang
    , Zhangchen Xu,
    Luyao Niu
    ,
    Bill Yuchen Lin
    ,
    Radha Poovendran
  3. KodCode: A Diverse, Challenging, and Verifiable Synthetic Dataset for Coding
    ACL 2025 · Zhangchen Xu,
    Yang Liu
    ,
    Yueqin Yin
    ,
    Mingyuan Zhou
    ,
    Radha Poovendran
  4. Magpie: Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with Nothing
    ICLR 2025 · Zhangchen Xu,
    Fengqing Jiang
    ,
    Luyao Niu
    ,
    Yuntian Deng
    ,
    Radha Poovendran
    ,
    Yejin Choi
    ,
    Bill Yuchen Lin
  5. SafeChain: Safety of Language Models with Long Chain-of-Thought Reasoning Capabilities
    ACL 2025 ·
    Fengqing Jiang
    , Zhangchen Xu,
    Yuetai Li
    ,
    Luyao Niu
    ,
    Zhen Xiang
    ,
    Bo Li
    ,
    Bill Yuchen Lin
    ,
    Radha Poovendran
  6. Small Models Struggle to Learn from Strong Reasoners
    ACL 2025 ·
    Yuetai Li
    ,
    Xiang Yue
    , Zhangchen Xu,
    Fengqing Jiang
    ,
    Luyao Niu
    ,
    Bill Yuchen Lin
    ,
    Bhaskar Ramasubramanian
    ,
    Radha Poovendran
  7. Stronger Models are Not Always Stronger Teachers for Instruction Tuning
    NAACL 2025 · Zhangchen Xu,
    Fengqing Jiang
    ,
    Luyao Niu
    ,
    Bill Yuchen Lin
    ,
    Radha Poovendran
  8. ACE: A Model Poisoning Attack on Contribution Evaluation Methods in Federated Learning
    USENIX Security 2024 · Zhangchen Xu,
    Fengqing Jiang
    ,
    Luyao Niu
    ,
    Jinyuan Jia
    ,
    Bo Li
    ,
    Radha Poovendran
  9. ArtPrompt: ASCII Art-based Jailbreak Attacks against Aligned LLMs
    ACL 2024 ·
    Fengqing Jiang
    , Zhangchen Xu,
    Luyao Niu
    ,
    Zhen Xiang
    ,
    Bhaskar Ramasubramanian
    ,
    Bo Li
    ,
    Radha Poovendran
  10. CleanGen: Mitigating Backdoor Attacks for Generation Tasks in Large Language Models
    EMNLP 2024 ·
    Yuetai Li
    , Zhangchen Xu,
    Fengqing Jiang
    ,
    Luyao Niu
    ,
    Dinuka Sahabandu
    ,
    Bhaskar Ramasubramanian
    ,
    Radha Poovendran
  11. POSTER: Identifying and Mitigating Vulnerabilities in LLM-Integrated Applications
    AsiaCCS 2024 ·
    Fengqing Jiang
    , Zhangchen Xu,
    Luyao Niu
    ,
    Boxin Wang
    ,
    Jinyuan Jia
    ,
    Bo Li
    ,
    Radha Poovendran
  12. Poster: Brave: Byzantine-Resilient and Privacy-Preserving Peer-to-Peer Federated Learning
    AsiaCCS 2024 · Zhangchen Xu,
    Fengqing Jiang
    ,
    Luyao Niu
    ,
    Jinyuan Jia
    ,
    Radha Poovendran
  13. SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding
    ACL 2024 · Zhangchen Xu,
    Fengqing Jiang
    ,
    Luyao Niu
    ,
    Jinyuan Jia
    ,
    Bill Yuchen Lin
    ,
    Radha Poovendran