3 citations · 7 across the 9 of their papers we have counts for
10 papers
Towards Mitigating Deceptive Safety Alignment in Large Reasoning Models
Xiangyu Zhou, Saleh Zare Zade, Rafi Ibn Sultan +2
Large Reasoning Models (LRMs) are commonly trained with reinforcement learning (RL) to improve their generation of chain-of-thought (CoT) reasoning before producing final answers.…
Alignment of LRMs via Counter-Aligned Few-Shot Conversation Exposure
Xiangyu Zhou, Saleh Zare Zade, Dongxiao Zhu
Large Reasoning Models (LRMs) rely on explicit chain-of-thought (CoT) reasoning and large context windows to achieve strong performance on complex tasks, but these features also in…
Attention Smoothing Is All You Need For Unlearning
Saleh Zare Zade, Xiangyu Zhou, Sijia Liu +1
Large Language Models are prone to memorizing sensitive, copyrighted, or hazardous content, posing significant privacy and legal concerns. Retraining from scratch is computationall…
Not All Tokens Are Meant to Be Forgotten
Xiangyu Zhou, Yao Qiang, Saleh Zare Zade +3
Large Language Models (LLMs), pre-trained on massive text corpora, exhibit remarkable human-level language understanding, reasoning, and decision-making abilities. However, they te…
Automatic Calibration for Membership Inference Attack on Large Language Models
Saleh Zare Zade, Yao Qiang, Xiangyu Zhou +4
Membership Inference Attacks (MIAs) have recently been employed to determine whether a specific text was part of the pre-training data of Large Language Models (LLMs). However, exi…
Generative LLM Powered Conversational AI Application for Personalized Risk Assessment: A Case Study in COVID-19
Mohammad Amin Roshani, Xiangyu Zhou, Yao Qiang +4
Large language models (LLMs) have shown remarkable capabilities in various natural language tasks and are increasingly being applied in healthcare domains. This work demonstrates a…
Learning to Poison Large Language Models for Downstream Manipulation
Xiangyu Zhou, Yao Qiang, Saleh Zare Zade +4
The advent of Large Language Models (LLMs) has marked significant achievements in language processing and reasoning capabilities. Despite their advancements, LLMs face vulnerabilit…
MFABA: A More Faithful and Accelerated Boundary-based Attribution Method for Deep Neural Networks
Zhiyu Zhu, Huaming Chen, Jiayu Zhang +5
To better understand the output of deep neural networks (DNN), attribution based methods have been an important approach for model interpretability, which assign a score for each i…
Hijacking Large Language Models via Adversarial In-Context Learning
Xiangyu Zhou, Yao Qiang, Saleh Zare Zade +2
In-context learning (ICL) has emerged as a powerful paradigm leveraging LLMs for specific downstream tasks by utilizing labeled examples as demonstrations (demos) in the preconditi…
Towards Trustworthy Artificial Intelligence for Equitable Global Health
Hong Qin, Jude Kong, Wandi Ding +14
Artificial intelligence (AI) can potentially transform global health, but algorithmic bias can exacerbate social inequities and disparity. Trustworthy AI entails the intentional de…