38 citations · 42 across the 12 of their papers we have counts for
13 papers
Break Me If You Can: Self-Jailbreaking of Aligned LLMs via Lexical Insertion Prompting
Devang Kulshreshtha, Hang Su, Haibo Jin +2
We introduce \emph{self-jailbreaking}, a threat model in which an aligned LLM guides its own compromise. Unlike most jailbreak techniques, which often rely on handcrafted prompts o…
Optimal Aggregation of LLM and PRM Signals for Efficient Test-Time Scaling
Peng Kuang, Yanli Wang, Xiaoyu Han +3
Process reward models (PRMs) are a cornerstone of test-time scaling (TTS), designed to verify and select the best responses from large language models (LLMs). However, this promise…
Improving Noise Efficiency in Privacy-preserving Dataset Distillation
Runkai Zheng, Vishnu Asutosh Dasu, Yinong Oliver Wang +2
Modern machine learning models heavily rely on large datasets that often include sensitive and private information, raising serious privacy concerns. Differentially private (DP) da…
Tracing LLM Reasoning Processes with Strategic Games: A Framework for Planning, Revision, and Resource-Constrained Decision Making
Xiaopeng Yuan, Xingjian Zhang, Ke Xu +5
Large language models (LLMs) are increasingly used for tasks that require complex reasoning. Most benchmarks focus on final outcomes but overlook the intermediate reasoning steps -…
Examining Alignment of Large Language Models through Representative Heuristics: The Case of Political Stereotypes
Sullam Jeoung, Yubin Ge, Haohan Wang +1
Examining the alignment of large language models (LLMs) has become increasingly important, e.g., when LLMs fail to operate as intended. This study examines the alignment of LLMs wi…
Conflict-Aware Adversarial Training
Zhiyu Xue, Haohan Wang, Yao Qin +1
Adversarial training is the most effective method to obtain adversarial robustness for deep neural networks by directly involving adversarial samples in the training procedure. To…
The Devil is in the Edges: Monocular Depth Estimation with Edge-aware Consistency Fusion
Pengzhi Li, Yikang Ding, Haohan Wang +2
This paper presents a novel monocular depth estimation method, named ECFNet, for estimating high-quality monocular depth with clear edges and valid overall structure from a single…
BadLabel: A Robust Perspective on Evaluating and Enhancing Label-noise Learning
Jingfeng Zhang, Bo Song, Haohan Wang +4
Label-noise learning (LNL) aims to increase the model's generalization given training data with noisy labels. To facilitate practical LNL algorithms, researchers have proposed diff…
Toward Robust Diagnosis: A Contour Attention Preserving Adversarial Defense for COVID-19 Detection
Kun Xiang, Xing Zhang, Jinwen She +4
As the COVID-19 pandemic puts pressure on healthcare systems worldwide, the computed tomography image based AI diagnostic system has become a sustainable solution for early diagnos…
A Principled Evaluation Protocol for Comparative Investigation of the Effectiveness of DNN Classification Models on Similar-but-non-identical Datasets
Esla Timothy Anzaku, Haohan Wang, Arnout Van Messem +1
Deep Neural Network (DNN) models are increasingly evaluated using new replication test datasets, which have been carefully created to be similar to older and popular benchmark data…
Bear the Query in Mind: Visual Grounding with Query-conditioned Convolution
Chonghan Chen, Qi Jiang, Chih-Hao Wang +4
Visual grounding is a task that aims to locate a target object according to a natural language expression. As a multi-modal task, feature interaction between textual and visual inp…
Measure and Improve Robustness in NLP Models: A Survey
Xuezhi Wang, Haohan Wang, Diyi Yang
As NLP models achieved state-of-the-art performances over benchmarks and gained wide applications, it has been increasingly important to ensure the safe deployment of these models…
Robust Contrastive Learning Using Negative Samples with Diminished Semantics
Songwei Ge, Shlok Mishra, Haohan Wang +2
Unsupervised learning has recently made exceptional progress because of the development of more effective contrastive learning methods. However, CNNs are prone to depend on low-lev…