cs.CLJan 23, 2026

Mitigating Bias in Automated Essay Scoring for ESL Learners via Contrastive Learning

Authors: Kevin Fan, Eric Yun

Organizations: Georgia Institute of Technology · Georgia State University

Read PDF
Ask AI
Cite

Copy citation

DOINot available for this paper

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.

Explore similar work

CardsList

  1. MAPLE: A Meta-learning Framework for Cross-Prompt Essay Scoring

    Apr 19, 2026Salam Albatarni, May Bashendy, Sohaila Eltanbouly +1Automated Essay ScoringMeta-Learning

    Computer Science and Engineering Department, Qatar University

  2. ICLE++: Modeling Fine-Grained Traits for Holistic Essay Scoring

    Jul 30, 2026Shengjie Li, Vincent NgAutomated Essay ScoringScoring

    Human Language Technology Research Institute University of Texas at Dallas Richardson, TX 75080-0688

  3. Error-Supervised Synthetic Learner Writing for Automated Essay Scoring

    Sep 20, 2026Duy Anh NguyenAutomated Essay ScoringSynthetic Training Data

    University of Greenwich, London, United Kingdom · FPT University, Can Tho, Vietnam