Automated Essay Scoring for Brazilian Portuguese. Evidence from Cross-Prompt Evaluation of ENEM Essays

André Barbosa, Denis Deratani Mauá


Abstract
Brazil’s ENEM, a high-stakes assessment determining university admission for millions of students annually, creates an immense evaluation burden where human raters process hundreds of essays daily. Automated Essay Scoring (AES) offers a potential solution, yet Portuguese-language systems remain understudied due to fragmented datasets and the complexity of ENEM’s multi-trait rubric. This work investigated cross-prompt, trait-specific essay scoring using a corpus of 385 essays across 38 prompts, where models evaluated essays on unseen prompts across five traits scored on a six-point ordinal scale. We compared three model classes: feature-based methods (72 features), encoder-only transformers (109M–1.5B parameters), and decoder architectures (2.4B–671B parameters) with fine-tuned and zero-shot configurations. Experiments under varying information access and rubric conditioning revealed that no single approach serves all evaluation needs: encoder models excel at mechanical traits (fluency, cohesion) despite context limitations; decoder models achieve superior performance on argumentation (QWK 0.73) and writing style (QWK 0.60) when provided full context; and language-specific pretraining benefits only surface-level features without improving complex reasoning. Best-performing models achieved QWK scores of 0.60–0.73. Gaps to oracle bounds ranged from 0.15 (argumentation) to 0.29 (writing style), with the largest disparities in writing style and persuasiveness.
Anthology ID:
2026.propor-2.11
Volume:
Proceedings of the 17th International Conference on Computational Processing of Portuguese (PROPOR 2026) - Vol. 2
Month:
April
Year:
2026
Address:
Salvador, Brazil
Editors:
Marlo Souza, Iria de-Dios-Flores, Diana Santos, Larissa Freitas, Jackson Wilke da Cruz Souza, Eugénio Ribeiro
Venue:
PROPOR
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
43–48
Language:
URL:
https://aclanthology.org/2026.propor-2.11/
DOI:
Bibkey:
Cite (ACL):
André Barbosa and Denis Deratani Mauá. 2026. Automated Essay Scoring for Brazilian Portuguese. Evidence from Cross-Prompt Evaluation of ENEM Essays. In Proceedings of the 17th International Conference on Computational Processing of Portuguese (PROPOR 2026) - Vol. 2, pages 43–48, Salvador, Brazil. Association for Computational Linguistics.
Cite (Informal):
Automated Essay Scoring for Brazilian Portuguese. Evidence from Cross-Prompt Evaluation of ENEM Essays (Barbosa & Mauá, PROPOR 2026)
Copy Citation:
PDF:
https://aclanthology.org/2026.propor-2.11.pdf