版本更新 · v3arXiv:2601.16724
Mitigating Bias in Automated Essay Scoring for ESL Learners via Contrastive Learning
Kevin Fan, Eric Yun
原文摘要
Automated Essay Scoring systems disproportionately penalize high-proficiency English as a Second Language (ESL) learners. We propose Contrastive Learning with Matched Essay Pairs (CL-MEP), a bi-directional alignment strategy. CL-MEP reduces this scoring bias by 39.9% while improving overall accuracy, successfully disentangling valid syntactic complexity from surface-level grammatical errors.
cs.CL