Picture for Qiang Sheng

Qiang Sheng

PhantomHunter: Detecting Unseen Privately-Tuned LLM-Generated Text via Family-Aware Learning

Add code
Jun 18, 2025
Viaarxiv icon

From Judgment to Interference: Early Stopping LLM Harmful Outputs via Streaming Content Monitoring

Add code
Jun 11, 2025
Viaarxiv icon

Enhancing the Comprehensibility of Text Explanations via Unsupervised Concept Discovery

Add code
May 26, 2025
Viaarxiv icon

The Staircase of Ethics: Probing LLM Value Priorities through Multi-Step Induction to Complex Moral Dilemmas

Add code
May 23, 2025
Viaarxiv icon

LLM-Generated Fake News Induces Truth Decay in News Ecosystem: A Case Study on Neural News Recommendation

Add code
Apr 29, 2025
Viaarxiv icon

Interactive Visual Assessment for Text-to-Image Generation Models

Add code
Nov 23, 2024
Viaarxiv icon

Vision-fused Attack: Advancing Aggressive and Stealthy Adversarial Text against Neural Machine Translation

Add code
Sep 08, 2024
Figure 1 for Vision-fused Attack: Advancing Aggressive and Stealthy Adversarial Text against Neural Machine Translation
Figure 2 for Vision-fused Attack: Advancing Aggressive and Stealthy Adversarial Text against Neural Machine Translation
Figure 3 for Vision-fused Attack: Advancing Aggressive and Stealthy Adversarial Text against Neural Machine Translation
Figure 4 for Vision-fused Attack: Advancing Aggressive and Stealthy Adversarial Text against Neural Machine Translation
Viaarxiv icon

FakingRecipe: Detecting Fake News on Short Video Platforms from the Perspective of Creative Process

Add code
Jul 23, 2024
Viaarxiv icon

Let Silence Speak: Enhancing Fake News Detection with Generated Comments from Large Language Models

Add code
May 26, 2024
Figure 1 for Let Silence Speak: Enhancing Fake News Detection with Generated Comments from Large Language Models
Figure 2 for Let Silence Speak: Enhancing Fake News Detection with Generated Comments from Large Language Models
Figure 3 for Let Silence Speak: Enhancing Fake News Detection with Generated Comments from Large Language Models
Figure 4 for Let Silence Speak: Enhancing Fake News Detection with Generated Comments from Large Language Models
Viaarxiv icon

Ten Words Only Still Help: Improving Black-Box AI-Generated Text Detection via Proxy-Guided Efficient Re-Sampling

Add code
Feb 14, 2024
Viaarxiv icon