3 papers
cs.CL2026
Selective Token-Level Cryptographic Redaction for Privacy-Preserving Clinical Deployment of Large Language Models
Farhan Sheth, Ziyuan Yang, Yongying Lan +1
While large language models (LLMs) are increasingly used for clinical applications, many existing pipelines require sending raw sensitive health information to remote servers for p…
cs.CL2026
MoCo: A One-Stop Shop for Model Collaboration Research
Shangbin Feng, Yuyang Bai, Ziyuan Yang +17
Advancing beyond single monolithic language models (LMs), recent research increasingly recognizes the importance of model collaboration, where multiple LMs collaborate, compose, an…
cs.CL2026
Among Us: Measuring and Mitigating Malicious Contributions in Model Collaboration Systems
Ziyuan Yang, Wenxuan Ding, Shangbin Feng +1
Language models (LMs) are increasingly used in collaboration: multiple LMs trained by different parties collaborate through routing systems, multi-agent debate, model merging, and…