Zhexin Zhang

Venues

Frequent coauthors

Papers

1. How Should We Enhance the Safety of Large Reasoning Models: An Empirical Study
   ACL 2026 · Zhexin Zhang
2. LASA: Language-Agnostic Semantic Alignment at the Semantic Bottleneck for LLM Safety
   ACL 2026 ·

   Junxiao Yang

   DBLP profile ↗ORCID search ↗
3. New Terms, New Toxicity: Consensus-based Chinese Neologism Toxicity Detection via Search-Augmented LLMs
   ACL 2026 ·

   Shiyao Cui

   DBLP profile ↗ORCID search ↗
4. When Smiley Turns Hostile: Interpreting How Emojis Trigger LLMs' Toxicity
   AAAI 2026 ·

   Shiyao Cui

   DBLP profile ↗ORCID search ↗
5. Guiding not Forcing: Enhancing the Transferability of Jailbreaking Attacks on LLMs via Removing Superfluous Constraints
   ACL 2025 ·

   Junxiao Yang

   DBLP profile ↗ORCID search ↗
6. JPS: Jailbreak Multimodal Large Language Models with Collaborative Visual Perturbation and Textual Steering
   ACM MM 2025 ·

   Renmiao Chen

   DBLP profile ↗ORCID search ↗
7. Knowledge-to-Jailbreak: Investigating Knowledge-driven Jailbreaking Attacks for Large Language Models
   SIGKDD 2025 ·

   Shangqing Tu

   DBLP profile ↗ORCID search ↗
8. LongSafety: Evaluating Long-Context Safety of Large Language Models
   ACL 2025 ·

   Yida Lu

   DBLP profile ↗ORCID search ↗
9. ShieldVLM: Safeguarding the Multimodal Implicit Toxicity via Deliberative Reasoning with LVLMs: ShieldVLM
   ACM MM 2025 ·

   Shiyao Cui

   DBLP profile ↗ORCID search ↗
10. A Design of Interface for Visual-Impaired People to Access Visual Information from Images Featuring Large Language Models and Visual Language Models
    CHI 2024 · Zhexin Zhang
11. Defending Large Language Models Against Jailbreaking Attacks Through Goal Prioritization
    ACL 2024 · Zhexin Zhang
12. SafetyBench: Evaluating the Safety of Large Language Models
    ACL 2024 · Zhexin Zhang
13. ShieldLM: Empowering LLMs as Aligned, Customizable and Explainable Safety Detectors
    EMNLP 2024 · Zhexin Zhang