Themis: Training Robust Multilingual Code Reward Models for Flexible Multi-Criteria Scoring
Paper • 2605.00754 • Published • 3
The Ubiquitous Knowledge Processing Lab researches natural language processing, text mining, eLearning, and digital humanities.
SciCoQA: Quality Assurance for Scientific Paper--Code Alignment
PeerQA: A Scientific Question Answering Dataset from Peer Reviews