分步指令与简单表格输出格式提升大语言模型的依存句法分析准确率
Step-by-step Instructions and a Simple Tabular Output Format Improve the Dependency Parsing Accuracy of LLMs
AI总结：
针对大语言模型在依存句法分析中输出结构有效性与准确率不足的问题，提出先做词性标注再预测句法关系的分步指令策略搭配简化类CoNLL-U格式，在17种语言数据集上取得SOTA准确率，多语言微调还可提升跨语言泛化能力。
摘要：
大语言模型（LLMs）的最新进展已在各类任务中展现出出色性能，但标准提示方法往往难以生成结构有效且准确的输出，在依存句法分析任务中尤为突出。我们提出一种新颖的分步指令策略：先进行通用词性标注，再预测句法中心词与依存标签，搭配简化类CoNLL-U的输出格式，在17种语言的Universal Dependencies数据集上取得了当前最优准确率，且无幻觉或数据污染问题。我们进一步证实，多语言微调可同时提升跨语言泛化性能。研究结果凸显了显式推理步骤在基于LLM的句法分析中的有效性，为基于括号的方法提供了可扩展、格式一致的替代方案。
英文摘要：
Recent advances in large language models (LLMs) have enabled impressive performance in various tasks. However, standard prompting often struggles to produce structurally valid and accurate outputs, especially in dependency parsing. We propose a novel step-by-step instruction strategy, where universal part-of-speech tagging precedes the prediction of syntactic heads and dependency labels, and a simplified CoNLL-U like output format, our method achieves state-of-the-art accuracy on Universal Dependencies datasets across 17 languages without hallucination or contamination. We further show that multilingual fine-tuning simultaneously improves cross-language generalization performance. Our results highlight the effectiveness of explicit reasoning steps in LLM-based parsing and offer a scalable, format-consistent alternative to bracket-based approaches.
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。
