0

Zhexin Zhang

Papers
18

Cite

Notes

Only stored in your browser.

Attribution

Affiliations & profile
Semantic Scholar
Attribution policy →
18papers

Authored papers

18

Guiding not Forcing: Enhancing the Transferability of Jailbreaking Attacks on LLMs via Removing Superfluous Constraints

arXiv 2025

2025

How Should We Enhance the Safety of Large Reasoning Models: An Empirical Study

arXiv 2025

2025

Be Careful When Fine-tuning On Open-Source LLMs: Your Fine-tuning Data Could Be Secretly Stolen!

arXiv 2025

2025

BARREL: Boundary-Aware Reasoning for Factual and Reliable LRMs

arXiv 2025

2025

LongSafety: Evaluating Long-Context Safety of Large Language Models

arXiv 2025

2025

ShieldLM: Empowering LLMs as Aligned, Customizable and Explainable Safety Detectors

arXiv 2024

2024

Agent-SafetyBench: Evaluating the Safety of LLM Agents

arXiv 2024

2024

From Theft to Bomb-Making: The Ripple Effect of Unlearning in Defending Against Jailbreak Attacks

arXiv 2024

2024

Knowledge-to-Jailbreak: Investigating Knowledge-driven Jailbreaking Attacks for Large Language Models

arXiv 2024

2024

Seeker: Towards Exception Safety Code Generation with Intermediate Language Agents Framework

arXiv 2024

2024

Safety Assessment of Chinese Large Language Models

arXiv 2023

2023

SafetyBench: Evaluating the Safety of Large Language Models

arXiv 2023

2023

Defending Large Language Models Against Jailbreaking Attacks Through Goal Prioritization

arXiv 2023

2023

Ethicist: Targeted Training Data Extraction Through Loss Smoothed Soft Prompting and Calibrated Confidence Estimation

arXiv 2023

2023

Unveiling the Implicit Toxicity in Large Language Models

arXiv 2023

2023

Persona-Guided Planning for Controlling the Protagonist's Persona in Story Generation

arXiv 2022

2022

MoralDial: A Framework to Train and Evaluate Moral Dialogue Systems via Moral Discussions

arXiv 2022

2022

OpenMEVA: A Benchmark for Evaluating Open-ended Story Generation Metrics

ACL 2021 5

2021

Affiliations

No known affiliations.

Frequent co-authors

10

from 18 papers