[Mova](https://md.mova.elamur.ai/free/en/) · [this page in HTML](https://mova.elamur.ai/free/en/docs/papers/authors/hiroshi-matsuda/)

[home](https://md.mova.elamur.ai/free/en/) / [docs](https://md.mova.elamur.ai/free/en/docs/) / [papers](https://md.mova.elamur.ai/free/en/docs/papers/) / [authors](https://md.mova.elamur.ai/free/en/docs/papers/authors/) / Hiroshi Matsuda

# Hiroshi Matsuda

2 paper cards in Mova's library · 2025–2026

Hiroshi Matsuda wrote 2 of the papers Mova reads, in 2025–2026, most of them on [Dependency parsing](https://md.mova.elamur.ai/free/en/docs/papers/topics/dependency-parsing/), [Treebanks](https://md.mova.elamur.ai/free/en/docs/papers/topics/treebanks/); often with [Masayuki Asahara](https://md.mova.elamur.ai/free/en/docs/papers/authors/masayuki-asahara/), Chunpeng Ma.

[OpenAlex](https://openalex.org/A5066539878) · [ORCID](https://orcid.org/0000-0002-6297-9897) · [**h-index 64**](https://openalex.org/authors/A5066539878) · [13892 citations](https://openalex.org/authors/A5066539878) · [610 works](https://openalex.org/works?filter=author.id:A5066539878) — openalex, 2026-10-18

The profile is the library's match of the name; two people with one name are not always told apart.

Elsewhere: [Google Scholar](https://scholar.google.com/citations?view_op=search_authors&mauthors=Hiroshi+Matsuda) · [Semantic Scholar](https://www.semanticscholar.org/search?q=Hiroshi+Matsuda) · [dblp](https://dblp.org/search?q=Hiroshi+Matsuda) · [ACL Anthology](https://aclanthology.org/search/?q=Hiroshi+Matsuda) · [ORCID](https://orcid.org/orcid-search/search?searchQuery=Hiroshi+Matsuda)

Topics: [Dependency parsing](https://md.mova.elamur.ai/free/en/docs/papers/topics/dependency-parsing/) 1 · [Treebanks](https://md.mova.elamur.ai/free/en/docs/papers/topics/treebanks/) 1

## Papers

1. **[Probing the Dynamics of Syntactic Ability Acquisition Throughout LLM Pretraining](https://md.mova.elamur.ai/free/en/docs/papers/matsuda-2026-probing-dynamics-syntactic-ability-acquisition/)** *(2026)* The authors study when syntactic skills appear during LLM pretraining and which ones stay weak. Their method, LoRA probing, keeps the base model frozen and trains only low-rank adapters to produce step-by-step UD parses in a simple tabular format. They apply it to the public intermediate checkpoints of OLMo-2-7B…
2. **[Step-by-step Instructions and a Simple Tabular Output Format Improve the Dependency Parsing Accuracy of LLMs](https://md.mova.elamur.ai/free/en/docs/papers/matsuda-2025-step-step-instructions-simple-tabular/)** *(2025)* The paper asks how to get structurally valid, accurate Universal Dependencies parses out of large language models.

## Co-authors (2)

- [Masayuki Asahara](https://md.mova.elamur.ai/free/en/docs/papers/authors/masayuki-asahara/) ×2
- Chunpeng Ma
- [← previous Hinrich Schütze](https://md.mova.elamur.ai/free/en/docs/papers/authors/hinrich-schutze/)
- [next → Hiroyuki Shindo](https://md.mova.elamur.ai/free/en/docs/papers/authors/hiroyuki-shindo/)
- [↑ back to Authors](https://md.mova.elamur.ai/free/en/docs/papers/authors/)