3 papers
cs.LG2026
DeconDTN-Toolkit: A Library for Evaluation and Enhancement of Robustness to Provenance Shift
Yongsen Tan, Zhecheng Sheng, Xiruo Ding +2
Despite the burgeoning body of work on distribution shifts, provenance shift-where the relationship between data source and label changes at deployment-remains poorly understood an…
cs.LG2026
When Prompts Interact: Assessing Prompt Arithmetic for Deconfounding under Distribution Shift
Zhecheng Sheng, Yongsen Tan, Xiruo Ding +2
In classification tasks, models may rely on confounding variables to achieve strong in-distribution performance, capturing spurious features that fail under distribution shift. Thi…
cs.CL2025
Mitigating Confounding in Speech-Based Dementia Detection through Weight Masking
Zhecheng Sheng, Xiruo Ding, Brian Hur +3
Deep transformer models have been used to detect linguistic anomalies in patient transcripts for early Alzheimer's disease (AD) screening. While pre-trained neural language models…