KF
Kevin Fan, Eric Yun
· 1 min read
ResearcharXiv cs.CL
Mitigating Bias in Automated Essay Scoring for ESL Learners via Contrastive Learning
arXiv:2601.16724v2 Announce Type: replace
Abstract: 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.
Original source
This story was published by arXiv cs.CL and written by Kevin Fan, Eric Yun. SyncAI.news shows a preview; the complete article is on the publisher's site.
Read the full story on arxiv.org
