# Step-by-step Instructions and a Simple Tabular Output Format Improve the Dependency Parsing Accuracy of LLMs

arXiv: https://arxiv.org/abs/2506.09983 · HTML: https://mlsanity.com/paper/2506.09983/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 17 references that are in the map.
- First posted on arXiv 11 Jun 2025.

## Builds on (most cited first, 7 of 7)

- [Membership Inference Attacks against Machine Learning Models](https://mlsanity.com/paper/1610.05820/) (2016)
- [Stanza: A Python Natural Language Processing Toolkit for Many Human Languages](https://mlsanity.com/paper/2003.07082/) (2020)
- [Universal Dependencies v2: An Evergrowing Multilingual Treebank Collection](https://mlsanity.com/paper/2004.10643/) (2020)
- [Security and Privacy Challenges of Large Language Models: A Survey](https://mlsanity.com/paper/2402.00888/) (2024)
- [Grammar as a Foreign Language](https://mlsanity.com/paper/1412.7449/) (2014)
- [Transition-Based Dependency Parsing with Stack Long Short-Term Memory](https://mlsanity.com/paper/1505.08075/) (2015)
- [Constituent Parsing as Sequence Labeling](https://mlsanity.com/paper/1810.08994/) (2018)

## Built on by (most cited first, 2 of 2)

- [Arabic Morphosyntactic Tagging and Dependency Parsing with Large Language Models](https://mlsanity.com/paper/2603.16718/) (2026)
- [CrisisKD: Five-Stage Knowledge Distillation for Aspect-Level Sentiment and Emotion Analysis in Crisis Discourse](https://mlsanity.com/paper/2609.05757/) (2026)

## Abstract (arXiv)

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.