182 citations · 356 across the 13 of their papers we have counts for
13 papers
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…
Can Public Large Language Models Help Private Cross-device Federated Learning?
Boxin Wang, Yibo Jacky Zhang, Yuan Cao +5
We study (differentially) private federated learning (FL) of language models. The language models in cross-device FL are relatively small, which can be trained with meaningful form…
Shall We Pretrain Autoregressive Language Models with Retrieval? A Comprehensive Study
Boxin Wang, Wei Ping, Peng Xu +9
Large decoder-only language models (LMs) can be largely improved in terms of perplexity by retrieval (e.g., RETRO), but its impact on text generation quality and downstream task ac…
A Note on "Efficient Task-Specific Data Valuation for Nearest Neighbor Algorithms"
Jiachen T. Wang, Ruoxi Jia
Data valuation is a growing research field that studies the influence of individual data points for machine learning (ML) models. Data Shapley, inspired by cooperative game theory…
FOCUS: Fairness via Agent-Awareness for Federated Learning on Heterogeneous Data
Wenda Chu, Chulin Xie, Boxin Wang +5
Federated learning (FL) allows agents to jointly train a global model without sharing their local data. However, due to the heterogeneous nature of local data, it is challenging to…
SemAttack: Natural Textual Attacks via Different Semantic Spaces
Boxin Wang, Chejian Xu, Xiangyu Liu +2
Recent studies show that pre-trained language models (LMs) are vulnerable to textual adversarial attacks. However, existing attack methods either suffer from low attack success rat…