Shengjie Li, Vincent Ng (2026) — arXiv:2607.27671 (cs.CL)
Summary
Introduces ICLE++, a corpus of persuasive student essays annotated with both holistic scores and trait-specific scores, addressing limitations of the widely-used ASAP corpus. Demonstrates that models trained on trait-specific annotations achieve better generalization across corpora for automated essay scoring.
The work connects to broader discussions in AI and education around automated-essay-scoring, writing-education, automated-grading, contributing to our understanding of how automated grading shapes educational practice.
Key Contributions
- Contributes empirical or theoretical advances relevant to the automated-essay-scoring domain
- Published in 2026, reflecting the fast-moving landscape of AI in education research
- Engages with questions of llm and writing education in educational contexts
Related Pages
Citation
APA: Shengjie Li, Vincent Ng (2026). ICLE++: Modeling Fine-Grained Traits for Holistic Essay Scoring. arXiv:2607.27671. cs.CL.