低资源印地语语法错误纠正的最小编辑指令微调
Minimal-Edit Instruction Tuning for Low-Resource Indic GEC
AI总结：
本文提出一种无需数据增强的低资源印地语语法错误纠正方法，通过指令微调和保守解码实现高效纠错。
摘要：
针对印地语语法错误纠正面临监督数据有限、脚本多样和形态丰富的问题，我们提出了一种无需数据增强的设置，利用指令微调的大语言模型和保守解码。一个12B的GEMMA 3模型在bnb 4位精度下进行指令微调，并通过参数高效微调（PEFT）和Alpaca式格式化。解码遵循一种确定性且约束意识的流程，使用轻量级正常化器以鼓励最小化且保持意义的编辑。我们通过固定的语言特定提示来操作推断，该提示直接从确定性错误分类器的分类学、标签分布和训练语料库中计算出的优先级顺序合成。在官方未微调的GLEU评估中，系统在马拉雅尔语上得分为92.41，排名第六；在印地语上得分为81.44，排名第三。这些结果表明，分类器指导的提示设计、基于适配器的指令微调和确定性解码为印地语语法错误纠正提供了一种可重复且计算高效的方法，替代了以数据增强为中心的管道。该方法也促使未来工作在更强的形态语法约束和人类中心的保守编辑评估方面进行探索。
英文摘要：
Grammatical error correction for Indic languages faces limited supervision, diverse scripts, and rich morphology. We propose an augmentation-free setup that uses instruction-tuned large language models and conservative decoding. A 12B GEMMA 3 model is instruction-tuned in bnb 4-bit precision with parameter-efficient fine-tuning (PEFT) and Alpaca-style formatting. Decoding follows a deterministic, constraint-aware procedure with a lightweight normaliser that encourages minimal, meaning-preserving edits. We operationalise inference, subsequent to instruction fine-tuning (IFT), via a fixed, language-specific prompt directly synthesised from a deterministic error classifier's taxonomy, label distributions, and precedence ordering computed on the training corpus. Under the official untuned GLEU evaluation, the system scores 92.41 on Malayalam, sixth overall, and 81.44 on Hindi, third overall. These results indicate that classifier-informed prompt design, adapter-based instruction tuning, and deterministic decoding provide a reproducible and a computationally efficient alternative to augmentation-centred pipelines for Indic GEC. The approach also motivates future work on stronger morphosyntactic constraints and human-centred evaluation of conservative edits.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
