Zhexin Zhang
- Papers
- 18
Cite
Notes
Only stored in your browser.
Authored papers
18Guiding not Forcing: Enhancing the Transferability of Jailbreaking Attacks on LLMs via Removing Superfluous Constraints
arXiv 2025
How Should We Enhance the Safety of Large Reasoning Models: An Empirical Study
arXiv 2025
Be Careful When Fine-tuning On Open-Source LLMs: Your Fine-tuning Data Could Be Secretly Stolen!
arXiv 2025
BARREL: Boundary-Aware Reasoning for Factual and Reliable LRMs
arXiv 2025
LongSafety: Evaluating Long-Context Safety of Large Language Models
arXiv 2025
ShieldLM: Empowering LLMs as Aligned, Customizable and Explainable Safety Detectors
arXiv 2024
Agent-SafetyBench: Evaluating the Safety of LLM Agents
arXiv 2024
From Theft to Bomb-Making: The Ripple Effect of Unlearning in Defending Against Jailbreak Attacks
arXiv 2024
Knowledge-to-Jailbreak: Investigating Knowledge-driven Jailbreaking Attacks for Large Language Models
arXiv 2024
Seeker: Towards Exception Safety Code Generation with Intermediate Language Agents Framework
arXiv 2024
Safety Assessment of Chinese Large Language Models
arXiv 2023
SafetyBench: Evaluating the Safety of Large Language Models
arXiv 2023
Defending Large Language Models Against Jailbreaking Attacks Through Goal Prioritization
arXiv 2023
Ethicist: Targeted Training Data Extraction Through Loss Smoothed Soft Prompting and Calibrated Confidence Estimation
arXiv 2023
Unveiling the Implicit Toxicity in Large Language Models
arXiv 2023
Persona-Guided Planning for Controlling the Protagonist's Persona in Story Generation
arXiv 2022
MoralDial: A Framework to Train and Evaluate Moral Dialogue Systems via Moral Discussions
arXiv 2022
OpenMEVA: A Benchmark for Evaluating Open-ended Story Generation Metrics
ACL 2021 5
Affiliations
Frequent co-authors
10from 18 papers