Research Papers 论文研究 16h ago Updated 18m ago 更新于 18分钟前 35

Larger Context Window, Fewer Overcorrections: Optimizing Prompts and Batching for Minimal-Edit Grammatical Error Correction Larger Context Window, Fewer Overcorrections: Optimizing Prompts and Batching for Minimal-Edit Grammatical Error Correction

Minimal-edit GEC is a persistent challenge for zero/few-shot LLMs, which systematically overcorrect and degrade F0.5 by rewriting well-formed text spans Three prompt-based advances close the gap to fine-tuned models: taxonomy-based instructions with comprehensive grammatical error rules, batching multiple sentences as a regularizer against overcorrection, and LLM-assisted prompt optimization Batching multiple uncorrected sentences into a single context acts as a targeted regularizer, hypothesize 提出基于提示的最小编辑语法错误纠正方法,通过分类法指令、批量处理和LLM辅助优化三个技术改进,显著缩小与微调模型的差距 批量处理多个未纠正句子作为针对过度纠正的正则化器,利用自注意力机制的注意力稀释效应系统性地降低编辑率 在BEA-2019测试集上达到F0.5=78.32,建立新的基于提示的SOTA,与微调单模型SOTA的差距仅0.38分 代码、提示和输出已公开,为资源受限场景提供高效的GEC解决方案

50
Hot 热度
50
Quality 质量
50
Impact 影响力

Analysis 深度分析

TL;DR

  • Minimal-edit GEC is a persistent challenge for zero/few-shot LLMs, which systematically overcorrect and degrade F0.5 by rewriting well-formed text spans
  • Three prompt-based advances close the gap to fine-tuned models: taxonomy-based instructions with comprehensive grammatical error rules, batching multiple sentences as a regularizer against overcorrection, and LLM-assisted prompt optimization
  • Batching multiple uncorrected sentences into a single context acts as a targeted regularizer, hypothesized to arise from an attention dilution effect induced by the bounded capacity of self-attention scores
  • The approach achieves F0.5=78.32 on BEA-2019 test set using Gemini 3.1-Pro, establishing a new prompt-based SOTA and narrowing the gap to fine-tuned SOTA to just 0.38 points
  • Code, prompts, and outputs are publicly available, lowering the infrastructure barrier for high-quality GEC

Why It Matters

This work demonstrates that carefully engineered prompting strategies can nearly match fine-tuned model performance on a challenging NLP task, offering a cost-effective alternative to expensive fine-tuning pipelines. For AI practitioners working on language quality tools, it provides a practical framework for reducing overcorrection—a pervasive failure mode in LLM-based text editing—without requiring dedicated training infrastructure.

Technical Details

  • Taxonomy-based instructions: The authors introduce a comprehensive list of grammatical error rules that bound the LLM's scope of correctable edits, aligning model behavior with the F0.5 evaluation metric. This approach benefits the strongest models while remaining model-dependent overall.
  • Batching as regularization: Multiple uncorrected sentences are batched into a single input context, which systematically reduces the edit rate across diverse LLM families. The hypothesized mechanism is an attention dilution effect caused by the bounded capacity of self-attention scores.
  • LLM-assisted Prompt Optimization: Gemini 3.1-Pro is used to iteratively refine the prompt instructions, automating what would otherwise be manual prompt engineering.
  • Benchmark performance: Achieves F0.5=78.32 on the BEA-2019 test set, establishing a new prompt-based state-of-the-art and closing the gap to the fine-tuned single-model SOTA (Staruch et al., 2025) to just 0.38 points.
  • Minimal-edit constraint: The core technical challenge addressed is preventing LLMs from rewriting well-formed spans—a systematic overcorrection behavior that degrades precision without improving recall.

Industry Insight

  • The attention dilution hypothesis from batching suggests a generalizable technique for controlling LLM aggressiveness in editing tasks, potentially applicable beyond GEC to code correction, summarization, and other text transformation pipelines.
  • The near-parity between prompt-based and fine-tuned approaches (0.38-point gap) signals that for many production GEC use cases, organizations can skip expensive fine-tuning and invest in prompt engineering instead, significantly reducing infrastructure costs and time-to-deployment.
  • As LLM context windows continue to grow, the batching strategy becomes increasingly viable—practitioners should experiment with larger batch sizes to further suppress overcorrection in their own text editing applications.

TL;DR

  • 提出基于提示的最小编辑语法错误纠正方法,通过分类法指令、批量处理和LLM辅助优化三个技术改进,显著缩小与微调模型的差距
  • 批量处理多个未纠正句子作为针对过度纠正的正则化器,利用自注意力机制的注意力稀释效应系统性地降低编辑率
  • 在BEA-2019测试集上达到F0.5=78.32,建立新的基于提示的SOTA,与微调单模型SOTA的差距仅0.38分
  • 代码、提示和输出已公开,为资源受限场景提供高效的GEC解决方案

为什么值得看

该研究为语法错误纠正提供了无需微调的高效方案,通过提示工程而非大规模计算资源实现接近微调模型的性能。批量处理策略的创新应用展示了如何利用模型架构特性来改善输出质量,对NLP工程实践具有重要参考价值。

技术解析

  • 基于分类法的指令(Taxonomy-based Instructions):引入全面的语法错误规则分类列表,为LLM提供有边界的、与评估指标对齐的可纠正编辑范围,强制执行最小编辑约束,对最强模型效果显著
  • 批量处理正则化机制:将多个未纠正句子合并到单一输入上下文中,利用自注意力分数的有限容量产生注意力稀释效应,系统性地降低编辑率,减少过度纠正现象
  • LLM辅助提示优化:使用Gemini 3.1-Pro对提示进行精细化调整,在BEA-2019测试集上实现F0.5=78.32的分数,与微调单模型SOTA(Staruch et al., 2025)的差距仅0.38分

行业启示

  • 提示工程正在成为缩小与微调模型性能差距的有效途径,为算力受限场景提供了可行的替代方案,降低了GEC系统的部署门槛
  • 批量处理策略的创新应用展示了如何利用模型架构特性(如注意力机制)来改善输出质量,这一思路可推广到其他NLP任务
  • 最小编辑约束对于保持文本原意至关重要,过度纠正会损害文本质量,这一原则应成为GEC系统设计的核心考量

Disclaimer: The above content is generated by AI and is for reference only. 免责声明:以上内容由 AI 生成,仅供参考。