6 papers
Does AI Reviewer See the Full Picture? Attacking and Defending Multimodal Peer Review
Xinyu Zhao, Rana Muhammad Shahroz Khan, Zhen Xu +2
The integration of Large Language Models (LLMs) and Multimodal LLMs (MLLMs) into scientific peer-review workflows introduces novel and significant risks for adversarial manipulatio…
Detecting Functional Memorization in Code Language Models
Matthieu Meeus, Anil Ramakrishna, Shengyuan Hu +3
Large language models (LLMs) are increasingly used to generate code at scale. Meanwhile, prior work has investigated whether training data may be recoverable from model outputs, by…
ACTG-ARL: Differentially Private Conditional Text Generation with RL-Boosted Control
Yuzheng Hu, Ryan McKenna, Da Yu +4
Generating high-quality synthetic text under differential privacy (DP) is critical for training and evaluating language models without compromising user privacy. Prior work on synt…
MAPLE: Metadata Augmented Private Language Evolution
Eli Chien, Yuzheng Hu, Ryan McKenna +3
Differentially private (DP) fine-tuning of large language models (LLMs) requires massive compute and full model access, which rules out state-of-the-art proprietary APIs for genera…
Synthesizing Privacy-Preserving Text Data via Finetuning without Finetuning Billion-Scale LLMs
Bowen Tan, Zheng Xu, Eric Xing +2
Synthetic data offers a promising path to train models while preserving data privacy. Differentially private (DP) finetuning of large language models (LLMs) as data generator is ef…
Synthesizing and Adapting Error Correction Data for Mobile Large Language Model Applications
Yanxiang Zhang, Zheng Xu, Shanshan Wu +2
Error correction is an important capability when applying large language models (LLMs) to facilitate user typing on mobile devices. In this paper, we use LLMs to synthesize a high-…