Papers by Jiexin Kuang

Copied to clipboard

Challenge:	generative LLMs have been known for overcorrection where results obtain higher recall measures than precision measures.
Approach:	They propose to use generative LLMs to prompt grammatical error correction using a model based on language proficiency to examine the interaction between LLM's performance and L2 language proficiency.
Outcome:	The proposed model improves on zero-shot and few-shot prompting and fine-tuning models for grammatical error correction for learners of English as a foreign language based on the different proficiency levels.