Picture for Ziqing Yang

Ziqing Yang

More Data or Better Data? A Critical Analysis of Data Selection and Synthesis for Mathematical Reasoning

Add code
Oct 08, 2025
Viaarxiv icon

JADES: A Universal Framework for Jailbreak Assessment via Decompositional Scoring

Add code
Aug 28, 2025
Viaarxiv icon

MathSmith: Towards Extremely Hard Mathematical Reasoning by Forging Synthetic Problems with a Reinforced Policy

Add code
Aug 07, 2025
Viaarxiv icon

Hate in Plain Sight: On the Risks of Moderating AI-Generated Hateful Illusions

Add code
Jul 30, 2025
Viaarxiv icon

The Challenge of Identifying the Origin of Black-Box Large Language Models

Add code
Mar 06, 2025
Figure 1 for The Challenge of Identifying the Origin of Black-Box Large Language Models
Figure 2 for The Challenge of Identifying the Origin of Black-Box Large Language Models
Figure 3 for The Challenge of Identifying the Origin of Black-Box Large Language Models
Figure 4 for The Challenge of Identifying the Origin of Black-Box Large Language Models
Viaarxiv icon

Synthetic Artifact Auditing: Tracing LLM-Generated Synthetic Data Usage in Downstream Applications

Add code
Feb 02, 2025
Viaarxiv icon

SOS! Soft Prompt Attack Against Open-Source Large Language Models

Add code
Jul 03, 2024
Figure 1 for SOS! Soft Prompt Attack Against Open-Source Large Language Models
Figure 2 for SOS! Soft Prompt Attack Against Open-Source Large Language Models
Figure 3 for SOS! Soft Prompt Attack Against Open-Source Large Language Models
Figure 4 for SOS! Soft Prompt Attack Against Open-Source Large Language Models
Viaarxiv icon

Comprehensive Assessment of Jailbreak Attacks Against LLMs

Add code
Feb 08, 2024
Figure 1 for Comprehensive Assessment of Jailbreak Attacks Against LLMs
Figure 2 for Comprehensive Assessment of Jailbreak Attacks Against LLMs
Figure 3 for Comprehensive Assessment of Jailbreak Attacks Against LLMs
Figure 4 for Comprehensive Assessment of Jailbreak Attacks Against LLMs
Viaarxiv icon

SecurityNet: Assessing Machine Learning Vulnerabilities on Public Models

Add code
Oct 19, 2023
Viaarxiv icon

IDOL: Indicator-oriented Logic Pre-training for Logical Reasoning

Add code
Jun 27, 2023
Figure 1 for IDOL: Indicator-oriented Logic Pre-training for Logical Reasoning
Figure 2 for IDOL: Indicator-oriented Logic Pre-training for Logical Reasoning
Figure 3 for IDOL: Indicator-oriented Logic Pre-training for Logical Reasoning
Figure 4 for IDOL: Indicator-oriented Logic Pre-training for Logical Reasoning
Viaarxiv icon