Generative LLMs, including Arabic-specific ones, underperform a fine-tuned BERT model on Arabic essay scoring, with bilingual prompting giving the best LLM results.
In: Proceedings of the 37th IEEE/ACM International Conference on Automated Software Engineering, pp
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
How well can LLMs Grade Essays in Arabic?
Generative LLMs, including Arabic-specific ones, underperform a fine-tuned BERT model on Arabic essay scoring, with bilingual prompting giving the best LLM results.