Yiming Zhang

Automatic Generation of Adversarial Readable Chinese Texts

2022 · IEEE Transactions on Dependable and Secure Computing

Natural language processing (NLP) models are known vulnerable to adversarial examples, similar to image processing models. Studying adversarial texts is an essential step to improve the robustness of NLP models. However, existing studies mainly focus …

Effective Prompt Extraction from Language Models

2023 · arXiv (Cornell University)

The text generated by large language models is commonly controlled by prompting, where a prompt prepended to a user's query guides the model's output. The prompts used by companies to guide their models are often …

MixNet: A Runtime Reconfigurable Optical-Electrical Fabric for Distributed Mixture-of-Experts Training

2025

Mixture-of-Expert (MoE) models outperform conventional models by selectively activating different subnets, named experts, on a per-token basis. This gated computation generates dynamic communications that cannot be determined beforehand, challenging the existing GPU interconnects that remain …

Multiple Choice Questions based Multi-Interest Policy Learning for Conversational Recommendation

2022 · Proceedings of the ACM Web Conference 2022

Conversational recommendation system (CRS) is able to obtain fine-grained and dynamic user preferences based on interactive dialogue. Previous CRS assumes that the user has a clear target item, which often deviates from the real scenario, …

Active Example Selection for In-Context Learning

2022

With a handful of demonstration examples, large-scale language models demonstrate strong capability to perform various tasks by in-context learning from these examples, without any fine-tuning. We demonstrate that in-context learning performance can be highly unstable …