AI RESEARCH
BRIDGE the Gap: Mitigating Bias Amplification in Automated Scoring of English Language Learners via Inter-group Data Augmentation
arXiv CS.CL
•
ArXi:2602.23580v2 Announce Type: replace In the field of educational assessment, automated scoring systems increasingly rely on deep learning and large language models (LLMs). However, these systems face significant risks of bias amplification, where model prediction gaps between student groups become larger than those observed in