Saved in:
Bibliographic Details
Main Authors: Matsuda, Hiroshi, Ma, Chunpeng, Asahara, Masayuki
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2506.09983
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913895121158144
author Matsuda, Hiroshi
Ma, Chunpeng
Asahara, Masayuki
author_facet Matsuda, Hiroshi
Ma, Chunpeng
Asahara, Masayuki
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2506_09983
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Step-by-step Instructions and a Simple Tabular Output Format Improve the Dependency Parsing Accuracy of LLMs
Matsuda, Hiroshi
Ma, Chunpeng
Asahara, Masayuki
Computation and Language
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.
title Step-by-step Instructions and a Simple Tabular Output Format Improve the Dependency Parsing Accuracy of LLMs
topic Computation and Language
url https://arxiv.org/abs/2506.09983