62 citations · 116 across the 12 of their papers we have counts for
12 papers
Understanding Silent Data Corruption in LLM Training
Jeffrey Ma, Hengzhi Pei, Leonard Lausen +1
As the scale of training large language models (LLMs) increases, one emergent failure is silent data corruption (SDC), where hardware produces incorrect computations without explic…
TextGuard: Provable Defense against Backdoor Attacks on Text Classification
Hengzhi Pei, Jinyuan Jia, Wenbo Guo +2
Backdoor attacks have become a major security threat for deploying machine learning models in security-critical applications. Existing research endeavors have proposed many defense…
DecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT Models
Boxin Wang, Weixin Chen, Hengzhi Pei +16
Generative Pre-trained Transformer (GPT) models have exhibited exciting progress in their capabilities, capturing the interest of practitioners and the public alike. Yet, while the…
Better Context Makes Better Code Language Models: A Case Study on Function Call Argument Completion
Hengzhi Pei, Jinman Zhao, Leonard Lausen +2
Pretrained code language models have enabled great progress towards program synthesis. However, common approaches only consider in-file local context and thus miss information and…
Zero-Shot Classification by Logical Reasoning on Natural Language Explanations
Chi Han, Hengzhi Pei, Xinya Du +1
Humans can classify data of an unseen category by reasoning on its language explanations. This ability is owing to the compositional nature of language: we can combine previously s…
Your Autoregressive Generative Model Can be Better If You Treat It as an Energy-Based One
Yezhen Wang, Tong Che, Bo Li +4
Autoregressive generative models are commonly used, especially for those tasks involving sequential data. They have, however, been plagued by a slew of inherent flaws due to the in…
Towards Generating Real-World Time Series Data
Hengzhi Pei, Kan Ren, Yuqing Yang +3
Time series data generation has drawn increasing attention in recent years. Several generative adversarial network (GAN) based methods have been proposed to tackle the problem usua…
Improving Certified Robustness via Statistical Learning with Logical Reasoning
Zhuolin Yang, Zhikuan Zhao, Boxin Wang +8
Intensive algorithmic efforts have been made to enable the rapid improvements of certificated robustness for complex ML models recently. However, current robustness certification m…
Reinforcement-Learning based Portfolio Management with Augmented Asset Movement Prediction States
Yunan Ye, Hengzhi Pei, Boxin Wang +4
Portfolio management (PM) is a fundamental financial planning task that aims to achieve investment goals such as maximal profits or minimal risks. Its decision process involves con…
T3: Tree-Autoencoder Constrained Adversarial Text Generation for Targeted Attack
Boxin Wang, Hengzhi Pei, Boyuan Pan +3
Adversarial attacks against natural language processing systems, which perform seemingly innocuous modifications to inputs, can induce arbitrary mistakes to the target models. Thou…
The Secret Revealer: Generative Model-Inversion Attacks Against Deep Neural Networks
Yuheng Zhang, Ruoxi Jia, Hengzhi Pei +3
This paper studies model-inversion attacks, in which the access to a model is abused to infer information about the training data. Since its first introduction, such attacks have r…
A Concise Model for Multi-Criteria Chinese Word Segmentation with Transformer Encoder
Xipeng Qiu, Hengzhi Pei, Hang Yan +1
Multi-criteria Chinese word segmentation (MCCWS) aims to exploit the relations among the multiple heterogeneous segmentation criteria and further improve the performance of each si…