3 papers
cs.CL2026
Understanding Errors in LLM-Based Question Answering over Imperfect Tables
Baowen Zhang, Wei Fan, Ruman Wang +1
Answering questions over imperfect tables requires handling errors that can affect the answer. We investigate two challenges for large language models (LLMs): whether error discove…
cs.CV2026
ScaFE: Data-Efficient Scar Classification with LLM-Generated Clinical Feature Programs
Ruman Wang, Hangting Ye
Classifying pathological scars from clinical photographs requires distinguishing keloids from hypertrophic scars despite limited expert-labeled data and substantial acquisition var…
cs.CV2026
When LLMs Analyze Scars: From Images to Clinically-Meaningful Features
Ruman Wang, Hangting Ye
Medical image classification faces a fundamental dilemma: while deep learning models achieve remarkable performance at scale, real-world clinical scenarios often suffer from severe…