6 citations · 6 across the 8 of their papers we have counts for
10 papers
Understanding and Mitigating Hallucination Escape in Tool-Using LLM Agents
Peigui Qi, Kunsheng Tang, Yide Song +2
Large language models (LLMs) increasingly serve as autonomous agents that invoke external tools. However, this capability introduces tool hallucination, selecting incorrect tools o…
GlitchPatch: Repairing Glitch Tokens in Frozen Language Models via Local Retokenization
Kunsheng Tang, Peigui Qi, Yide Song +3
Glitch tokens are anomalous vocabulary entries that can cause large language models (LLMs) to produce outputs inconsistent with their inputs. Existing repair methods require access…
VLMShield: Efficient and Robust Defense of Vision-Language Models against Malicious Prompts
Peigui Qi, Kunsheng Tang, Yanpu Yu +7
Vision-Language Models (VLMs) face significant safety vulnerabilities from malicious prompt attacks due to weakened alignment during visual integration. Existing defenses suffer fr…
Revis: Sparse Latent Steering to Mitigate Object Hallucination in Large Vision-Language Models
Jialin Wu, Wei Shi, Han Shen +5
Despite the advanced capabilities of Large Vision-Language Models (LVLMs), they frequently suffer from object hallucination. One reason is that visual features and pretrained textu…
SafeGuider: Robust and Practical Content Safety Control for Text-to-Image Models
Peigui Qi, Kunsheng Tang, Wenbo Zhou +5
Text-to-image models have shown remarkable capabilities in generating high-quality images from natural language descriptions. However, these models are highly vulnerable to adversa…
PoseGuard: Pose-Guided Generation with Safety Guardrails
Kongxin Wang, Jie Zhang, Peigui Qi +3
Pose-guided video generation has become a powerful tool in creative industries, exemplified by frameworks like Animate Anyone. However, conditioning generation on specific poses in…
FinRipple: Aligning Large Language Models with Financial Market for Event Ripple Effect Awareness
Yuanjian Xu, Jianing Hao, Kunsheng Tang +4
Financial markets exhibit complex dynamics where localized events trigger ripple effects across entities. Previous event studies, constrained by static single-company analyses and…
GenderCARE: A Comprehensive Framework for Assessing and Reducing Gender Bias in Large Language Models
Kunsheng Tang, Wenbo Zhou, Jie Zhang +7
Large language models (LLMs) have exhibited remarkable capabilities in natural language generation, but they have also been observed to magnify societal biases, particularly those…
Controlling risks of AI in chemical science with agents
Jiyan He, Weitao Feng, Haoxiang Guan +11
Artificial intelligence is rapidly advancing scientific discovery, but this progress carries risks of misuse, such as the creation of harmful substances, or circumvention of establ…
Turning Your Strength into Watermark: Watermarking Large Language Model via Knowledge Injection
Shuai Li, Kejiang Chen, Kunsheng Tang +4
Large language models (LLMs) have demonstrated outstanding performance, making them valuable digital assets with significant commercial potential. Unfortunately, the LLM and its AP…