🧑‍🔬 Ryo Yoshida

Affiliations

🎓The University of TokyoTokyo · Japan2002–2026 · 236 paperscurrent🎓The University of OsakaOsaka · Japan2023–2026 · 3 paperscurrent🏛️Japan Science and Technology AgencyTokyo · Japan2008–2011 · 20 papers🎓University of TsukubaTsukuba · Japan1997–2010 · 19 papers🎓Kansai Medical UniversityOsaka · Japan1995–2013 · 14 papers🎓Nagoya Institute of TechnologyNagoya · Japan2015–2025 · 12 papers🎓Waseda UniversityTokyo · Japan1990–2020 · 12 papers🎓Shinshu UniversityMatsumoto · Japan2009–2023 · 9 papers🎓Tohoku UniversitySendai · Japan2009–2016 · 8 papers🎓Tokyo Women's Medical UniversityTokyo · Japan1994–1996 · 8 papers

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 43 more institutions on single bylines are not listed.

Topics

Psycholinguistics & language acquisition2Language models & pretraining1Evaluation & benchmarks1

Works by year

2020s

Papers

The most cited first (OpenAlex and our library).

1. Targeted Syntactic Evaluation on the Chomsky Hierarchy (2024 · 10 citations)
   The authors propose a new approach to Targeted Syntactic Evaluation. Rather than testing individual grammatical phenomena, they examine how language models handle constructions of varying complexity according to the Chomsky hierarchy. To this end, four artificial formal languages are constructed, each modeling a…
2. Developmentally-plausible Working Memory Shapes a Critical Period for Language Acquisition (2025 · 9 citations)
   LLMs need far more training data than children to reach comparable linguistic competence. Drawing on the Critical Period Hypothesis and Newport's Less-is-More Hypothesis, the authors test whether mimicking how children's working memory grows can make LM training more data-efficient. They model working-memory growth…
3. An Existence Proof for Neural Language Models That Can Explain Garden-Path Effects via Surprisal (2026 · 1 citation)
   Neural language models (LMs) estimate reading difficulty well on simple, naturalistic text. On garden-path sentences, however, their surprisal predicts far less slowdown than humans actually show. Several researchers have taken this gap as evidence that syntactic disambiguation cost lies outside surprisal theory.…
4. Rethinking the Relationship between the Power Law and Hierarchical Structures (2026)
   Across many corpora, the statistical dependence between linguistic units (phones, characters, words) weakens with distance following a power law rather than an exponential curve.

Also in our library

1 more work of theirs is in our library without a page here yet; it will appear as we publish them.

Co-authors here

4 co-authors with a page, the most papers together first.

• Yohei Oseki ×4
• Taiga Someya ×2
• Masato Mita
• Tatsuki Kuribayashi

Cited by

Papers of our library cite their works 18 times (of the 140 884 papers whose bibliographies we read); 2 citing papers with a page here →.

This page in Markdown → https://md.research.elamur.ai/free/en/authors/ryo-yoshida/