Advancing Student Writing Through Automated Syntax Feedback

2025-01-13

AI Summary

This study addresses the challenge of improving students’ English grammatical writing proficiency and the lack of fine-grained, pedagogically grounded feedback. To this end, we introduce Essay-Syntax-Instruct—the first structured instruction dataset explicitly designed for grammar-focused writing instruction. We perform instruction tuning on GPT-3.5-Turbo, Llama-2-7b/13b-chat-hf, and Mistral-7B-Instruct-v0.2. Our key contributions include: (1) a novel grammar error annotation schema aligned with linguistic categories (e.g., tense, articles, subject–verb agreement); and (2) a multi-dimensional evaluation framework assessing both detection and correction accuracy. This work presents the first systematic empirical validation of large language models’ tunability and pedagogical efficacy for fine-grained grammatical error correction. Experimental results demonstrate that instruction-tuned models significantly outperform their base counterparts across all targeted grammatical dimensions, achieving higher precision in both error identification and correction. These findings substantiate the feasibility and practical utility of such models as real-time, interpretable writing assistants in educational settings.

Technology Category

• Natural Language Processing: Syntax — Tagging, Chunking & Parsing
• Machine Learning: Large Multimodal Models (LMMs)
• Cognitive Modeling & Cognitive Systems: Computational Creativity

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Large language models for search
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

This study underscores the pivotal role of syntax feedback in augmenting the syntactic proficiency of students. Recognizing the challenges faced by learners in mastering syntactic nuances, we introduce a specialized dataset named Essay-Syntax-Instruct designed to enhance the understanding and application of English syntax among these students. Leveraging the capabilities of Large Language Models (LLMs) such as GPT3.5-Turbo, Llama-2-7b-chat-hf, Llama-2-13b-chat-hf, and Mistral-7B-Instruct-v0.2, this work embarks on a comprehensive fine-tuning process tailored to the syntax improvement task. Through meticulous evaluation, we demonstrate that the fine-tuned LLMs exhibit a marked improvement in addressing syntax-related challenges, thereby serving as a potent tool for students to identify and rectify their syntactic errors. The findings not only highlight the effectiveness of the proposed dataset in elevating the performance of LLMs for syntax enhancement but also illuminate a promising path for utilizing advanced language models to support language acquisition efforts. This research contributes to the broader field of language learning technology by showcasing the potential of LLMs in facilitating the linguistic development of Students.

Problem

• English grammar
• writing ability
• pedagogical strategies

Innovation

• Essay-Syntax-Instruct
• Advanced Computational Programs
• Computer-Assisted Language Learning