[Mova](https://md.mova.elamur.ai/free/en/) · [this page in HTML](https://mova.elamur.ai/free/en/docs/papers/matsuda-2026-probing-dynamics-syntactic-ability-acquisition/)

[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/) / Probing the Dynamics of Syntactic Ability Acquisition Throughout LLM Pretraining

# Probing the Dynamics of Syntactic Ability Acquisition Throughout LLM Pretraining

**Authors:** [Hiroshi Matsuda](https://md.mova.elamur.ai/free/en/docs/papers/authors/hiroshi-matsuda/), [Masayuki Asahara](https://md.mova.elamur.ai/free/en/docs/papers/authors/masayuki-asahara/) · **Year:** 2026 · **Venue:** Proceedings of the Ninth Workshop on Universal Dependencies (UDW 2026) **Link:** [aclanthology.org/2026.udw-1.1](https://aclanthology.org/2026.udw-1.1/) (ACL Anthology 2026.udw-1.1; DOI [10.63317/2n8gkp49p3wg](https://doi.org/10.63317/2n8gkp49p3wg)) **License of the paper:** [CC BY-NC 4.0](https://creativecommons.org/licenses/by-nc/4.0/) (ELRA, LREC proceedings) — [creativecommons.org/licenses/by-nc/4.0](https://creativecommons.org/licenses/by-nc/4.0/) — summary only

[**0** citations](https://openalex.org/works?filter=cites:W7166536666) openalex · 2026-10-18[Proceedings of the Ninth Workshop on Universal Dependencies (UDW 2026)](https://aclanthology.org/volumes/2026.udw-1/)[licence](https://creativecommons.org/licenses/by-nc/4.0/)

- [Publisher's page](https://aclanthology.org/2026.udw-1.1/)
- [PDF](https://aclanthology.org/2026.udw-1.1.pdf)
- [DOI 10.63317/2n8gkp49p3wg](https://doi.org/10.63317/2n8gkp49p3wg)
- [OpenAlex](https://openalex.org/W7166536666)

**Authors (2)**

1. [Hiroshi Matsuda](https://openalex.org/A5150421339) h 0 · 0 citations · 7 works
2. [Masayuki Asahara](https://openalex.org/A5002196974) [ORCID](https://orcid.org/0000-0002-5178-7275) · h 20 · 1446 citations · 172 works

Citations and author metrics from openalex (2026-10-18); authors with the same name are not always told apart.

## Summary

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, training adapters at 24 pretraining stages and testing on UD treebanks in 33 languages. To fit OLMo-2's short context window they design a compact two-step template that predicts tags first and then heads and labels together without repeating word forms; it roughly matches the three-step template in accuracy while halving the context and greatly increasing throughput. The output format is learned very early in pretraining. Although the model was pretrained on almost exclusively English text, it reaches LAS above 80 in most of the languages tested, but relations such as iobj and csubj are acquired late and remain unstable across many languages.

## How Mova uses it

- [A clausal subject — csubj, not nsubj](https://md.mova.elamur.ai/free/en/docs/en/seeds/errors/clausal-subject-csubj/) — the finding that csubj is late and unstable in LLMs supports a rule flagging `nsubj` on a VERB (a clausal subject should be `csubj`).
- [iobj — a bare noun before obj; "to X" — obl](https://md.mova.elamur.ai/free/en/docs/en/seeds/errors/iobj-bare-nominal/) and [iobj — only with double-object verbs](https://md.mova.elamur.ai/free/en/docs/en/seeds/errors/iobj-verb-classes/) — cited for iobj instability; the rules forbid `case` under `iobj` and `iobj` with verbs that only take a `to`-recipient (explain, describe, suggest...).
- [Verbs that take an indirect object](https://md.mova.elamur.ai/free/en/docs/en/seeds/lexicon/verb-iobj-licensors/) — listed among the sources for the lexical rule that only double-object verbs (171 lemmas from VerbNet classes) may license `iobj`.
- [Typical failures of LLM annotators for UD](https://md.mova.elamur.ai/free/en/docs/en/seeds/errors/llm-annotator-failure-modes/) — "unstable rare relations" is one entry in the catalogue of LLM annotation failures, pointing to the rules above.

## Effectiveness in Mova

Not measured separately. The paper explains why the rules target these relations; the rules themselves are checked against gold treebanks (for example, in EWT 2.18 `iobj` with a `case` dependent occurs 0 times out of 795, and `nsubj` on a VERB occurs 4 times), but those are rule-validation counts, not a measured contribution of the paper.

---

👨‍🔬💥

## Cite

The paper itself, not this card. BibTeX from the library's record of the work. [DOI 10.63317/2n8gkp49p3wg](https://doi.org/10.63317/2n8gkp49p3wg)

```
@inproceedings{matsuda2026probing,
  title = {{Probing the Dynamics of Syntactic Ability Acquisition Throughout LLM Pretraining}},
  author = {Matsuda, Hiroshi and Asahara, Masayuki},
  booktitle = {Proceedings of the Ninth Workshop on Universal Dependencies (UDW 2026)},
  year = {2026},
  doi = {10.63317/2n8gkp49p3wg},
  url = {https://doi.org/10.63317/2n8gkp49p3wg}
}
```

- [← previous 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/)
- [next → An English Grammar: Methodical, Analytical, and Historical](https://md.mova.elamur.ai/free/en/docs/papers/matzner-1874-english-grammar-methodical-analytical/)
- [↑ back to papers](https://md.mova.elamur.ai/free/en/docs/papers/)

## References

41 references, 0 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Laura Pérez-Mayos, Miguel Ballesteros, and Leo Wanner. 2021. How much pretraining data do language models need to learn syntax? In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 1571–1582, Online and Punta Cana, Dominican Republic. Association for Compu… [find](https://scholar.google.com/scholar?q=Laura+P%C3%A9rez%2DMayos%2C+Miguel+Ballesteros%2C+and+Leo+Wanner%2E+2021%2E+How+much+pretraining+data+do+language+models+need+to+learn+syntax%3F+In+Proceedings+of+the+2021+Conference+on+Empirical+Methods+in+Natural+La)
2. BigScience Workshop, :, Teven Le Scao, et al. 2023. Bloom: A 176b-parameter open-access multilingual language model. [find](https://scholar.google.com/scholar?q=BigScience+Workshop%2C+%3A%2C+Teven+Le+Scao%2C+et+al%2E+2023%2E+Bloom%3A+A+176b%2Dparameter+open%2Daccess+multilingual+language+model%2E)
3. Terra Blevins, Hila Gonen, and Luke Zettlemoyer. 2022. Analyzing the mono- and cross-lingual pretraining dynamics of multilingual language models. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 3575–3590, Abu Dhabi, United Arab Emirates. Association… [find](https://scholar.google.com/scholar?q=Terra+Blevins%2C+Hila+Gonen%2C+and+Luke+Zettlemoyer%2E+2022%2E+Analyzing+the+mono%2D+and+cross%2Dlingual+pretraining+dynamics+of+multilingual+language+models%2E+In+Proceedings+of+the+2022+Conference+on+Empirical+Me)
4. Qwen, :, An Yang, et al. 2025. Qwen2.5 technical report. [find](https://scholar.google.com/scholar?q=Qwen%2C+%3A%2C+An+Yang%2C+et+al%2E+2025%2E+Qwen2%2E5+technical+report%2E)
5. Team OLMo, Pete Walsh, et al. 2025. 2 olmo 2 furious. [find](https://scholar.google.com/scholar?q=Team+OLMo%2C+Pete+Walsh%2C+et+al%2E+2025%2E+2+olmo+2+furious%2E)
6. Yuanhe Tian, Fei Xia, and Yan Song. 2024. Large language models are no longer shallow parsers. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 7131–7142, Bangkok, Thailand. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Yuanhe+Tian%2C+Fei+Xia%2C+and+Yan+Song%2E+2024%2E+Large+language+models+are+no+longer+shallow+parsers%2E+In+Proceedings+of+the+62nd+Annual+Meeting+of+the+Association+for+Computational+Linguistics+%28Volume+1%3A+Lon)
7. Matthew S. Dryer and Martin Haspelmath, editors. 2013. WALS Online (v2020.4). Zenodo. [find](https://scholar.google.com/scholar?q=Matthew+S%2E+Dryer+and+Martin+Haspelmath%2C+editors%2E+2013%2E+WALS+Online+%28v2020%2E4%29%2E+Zenodo%2E)
8. Gemma Team, Morgane Riviere, et al. 2024. Gemma 2: Improving open language models at a practical size. [find](https://scholar.google.com/scholar?q=Gemma+Team%2C+Morgane+Riviere%2C+et+al%2E+2024%2E+Gemma+2%3A+Improving+open+language+models+at+a+practical+size%2E)
9. Aaron Grattafiori et al. 2024. The llama 3 herd of models. [find](https://scholar.google.com/scholar?q=Aaron+Grattafiori+et+al%2E+2024%2E+The+llama+3+herd+of+models%2E)
10. Hetong Wang, Pasquale Minervini, and Edoardo Ponti. 2024. Probing the emergence of cross-lingual alignment during LLM training. In Findings of the Association for Computational Linguistics: ACL 2024, pages 12159–12173, Bangkok, Thailand. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Hetong+Wang%2C+Pasquale+Minervini%2C+and+Edoardo+Ponti%2E+2024%2E+Probing+the+emergence+of+cross%2Dlingual+alignment+during+LLM+training%2E+In+Findings+of+the+Association+for+Computational+Linguistics%3A+ACL+2024%2C+)
11. Edward J Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen. 2022. LoRA: Low-rank adaptation of large language models. In International Conference on Learning Representations. [find](https://scholar.google.com/scholar?q=Edward+J+Hu%2C+Yelong+Shen%2C+Phillip+Wallis%2C+Zeyuan+Allen%2DZhu%2C+Yuanzhi+Li%2C+Shean+Wang%2C+Lu+Wang%2C+and+Weizhu+Chen%2E+2022%2E+LoRA%3A+Low%2Drank+adaptation+of+large+language+models%2E+In+International+Conference+on+L)
12. Jeffrey Li et al. 2025. Datacomp-lm: In search of the next generation of training sets for language models. [find](https://scholar.google.com/scholar?q=Jeffrey+Li+et+al%2E+2025%2E+Datacomp%2Dlm%3A+In+search+of+the+next+generation+of+training+sets+for+language+models%2E)
13. Language Resource References Zeyu Liu, Yizhong Wang, Jungo Kasai, Hannaneh Hajishirzi, and Noah A. Smith. 2021. Probing across time: What does RoBERTa know and Agić, Željko and Ljubešić, Nikola. 2015. Universal Dependencies for Croatian (that work for Serbian, too). INCOMA Ltd. Shoumen, BULGARIA. [find](https://scholar.google.com/scholar?q=Language+Resource+References+Zeyu+Liu%2C+Yizhong+Wang%2C+Jungo+Kasai%2C+Hannaneh+Hajishirzi%2C+and+Noah+A%2E+Smith%2E+2021%2E+Probing+across+time%3A+What+does+RoBERTa+know+and+Agi%C4%87%2C+%C5%BDeljko+and+Ljube%C5%A1i%C4%87%2C+Nikola%2E+2015%2E)
14. Asahara, Masayuki and Kanayama, Hiroshi and Tanaka, Takaaki and Miyao, Yusuke and Uematsu, Sumire and Mori, Shinsuke and Matsumoto, Yuji and Omura, Mai and Murawaki, Yugo. 2018. Universal Dependencies Version 2 for Japanese. European Language Resources Association (ELRA). [find](https://scholar.google.com/scholar?q=Asahara%2C+Masayuki+and+Kanayama%2C+Hiroshi+and+Tanaka%2C+Takaaki+and+Miyao%2C+Yusuke+and+Uematsu%2C+Sumire+and+Mori%2C+Shinsuke+and+Matsumoto%2C+Yuji+and+Omura%2C+Mai+and+Murawaki%2C+Yugo%2E+2018%2E+Universal+Dependencies)
15. Hajič, Jan and others. 2024. Prague Dependency Treebank - Consolidated 2.0 (PDT-C 2.0). LINDAT/CLARIAH-CZ digital library at the Institute of Formal and Applied Linguistics (ÚFAL). [find](https://scholar.google.com/scholar?q=Haji%C4%8D%2C+Jan+and+others%2E+2024%2E+Prague+Dependency+Treebank+%2D+Consolidated+2%2E0+%28PDT%2DC+2%2E0%29%2E+LINDAT%2FCLARIAH%2DCZ+digital+library+at+the+Institute+of+Formal+and+Applied+Linguistics+%28%C3%9AFAL%29%2E)
16. Anders Johannsen and Héctor Martínez Alonso and Barbara Plank. 2015. Universal Dependencies for Danish. [find](https://scholar.google.com/scholar?q=Anders+Johannsen+and+H%C3%A9ctor+Mart%C3%ADnez+Alonso+and+Barbara+Plank%2E+2015%2E+Universal+Dependencies+for+Danish%2E)
17. Batanović, Vuk and Ljubešić, Nikola and Samardžić, Tanja and Erjavec, Tomaž. 2018. Training corpus SETimes.SR 1.0. Slovenian language resource repository CLARIN.SI. [find](https://scholar.google.com/scholar?q=Batanovi%C4%87%2C+Vuk+and+Ljube%C5%A1i%C4%87%2C+Nikola+and+Samard%C5%BEi%C4%87%2C+Tanja+and+Erjavec%2C+Toma%C5%BE%2E+2018%2E+Training+corpus+SETimes%2ESR+1%2E0%2E+Slovenian+language+resource+repository+CLARIN%2ESI%2E)
18. Lynn, Teresa and Foster, Jennifer. 2016. Universal Dependencies for Irish. Association pour le Traitement Automatique des Langues. Dépendances universelles de l’irlandais. [find](https://scholar.google.com/scholar?q=Lynn%2C+Teresa+and+Foster%2C+Jennifer%2E+2016%2E+Universal+Dependencies+for+Irish%2E+Association+pour+le+Traitement+Automatique+des+Langues%2E+D%C3%A9pendances+universelles+de+l%E2%80%99irlandais%2E)
19. Agnė Bielinskienė and Loïc Boizou and Jolanta Kovalevskaitė and Erika Rimkutė. 2016. Lithuanian Dependency Treebank ALKSNIS. In: I. Skadin , a and R. Rozis (Eds.): Human Language Technologies – The Baltic Perspective. Amsterdam: IOS Press. [find](https://scholar.google.com/scholar?q=Agne%CC%87+Bielinskiene%CC%87+and+Lo%C3%AFc+Boizou+and+Jolanta+Kovalevskaite%CC%87+and+Erika+Rimkute%CC%87%2E+2016%2E+Lithuanian+Dependency+Treebank+ALKSNIS%2E+In%3A+I%2E+Skadin+%2C+a+and+R%2E+Rozis+%28Eds%2E%29%3A+Human+Language+Technologies+%E2%80%93+Th)
20. Marşan, Büşra and Akkurt, Salih Furkan and Şen, Muhammet and Gürbüz, Merve and Güngör, Onur and Özateş, Şaziye Betül and Üsküdarlı, Suzan and Özgür, Arzucan and Güngör, Tunga and Öztürk, Balkız. 2022. Enhancements to the BOUN Treebank Reflecting the Agglutinative Nature of Turkish. [find](https://scholar.google.com/scholar?q=Mar%C5%9Fan%2C+B%C3%BC%C5%9Fra+and+Akkurt%2C+Salih+Furkan+and+%C5%9Een%2C+Muhammet+and+G%C3%BCrb%C3%BCz%2C+Merve+and+G%C3%BCng%C3%B6r%2C+Onur+and+%C3%96zate%C5%9F%2C+%C5%9Eaziye+Bet%C3%BCl+and+%C3%9Csk%C3%BCdarl%C4%B1%2C+Suzan+and+%C3%96zg%C3%BCr%2C+Arzucan+and+G%C3%BCng%C3%B6r%2C+Tunga+and+%C3%96zt%C3%BCrk%2C+Balk%C4%B1z%2E+2022%2E)
21. Bosco, Cristina and Montemagni, Simonetta and Simi, Maria. 2013. Converting Italian Treebanks: Towards an Italian Stanford Dependency Treebank. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Bosco%2C+Cristina+and+Montemagni%2C+Simonetta+and+Simi%2C+Maria%2E+2013%2E+Converting+Italian+Treebanks%3A+Towards+an+Italian+Stanford+Dependency+Treebank%2E+Association+for+Computational+Linguistics%2E)
22. McDonald, Ryan and Nivre, Joakim and Quirmbach-Brundage, Yvonne and Goldberg, Yoav and Das, Dipanjan and Ganchev, Kuzman and Hall, Keith and Petrov, Slav and Zhang, Hao and Täckström, Oscar and Bedini, Claudia and Bertomeu Castelló, Núria and Lee, Jungmee. 2013. Universal Dependency Annotation for M… [find](https://scholar.google.com/scholar?q=McDonald%2C+Ryan+and+Nivre%2C+Joakim+and+Quirmbach%2DBrundage%2C+Yvonne+and+Goldberg%2C+Yoav+and+Das%2C+Dipanjan+and+Ganchev%2C+Kuzman+and+Hall%2C+Keith+and+Petrov%2C+Slav+and+Zhang%2C+Hao+and+T%C3%A4ckstr%C3%B6m%2C+Oscar+and+Bedini)
23. Bouma, Gosse and van Noord, Gertjan. 2017. Increasing Return on Annotation Investment: The Automatic Construction of a Universal Dependency Treebank for Dutch. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Bouma%2C+Gosse+and+van+Noord%2C+Gertjan%2E+2017%2E+Increasing+Return+on+Annotation+Investment%3A+The+Automatic+Construction+of+a+Universal+Dependency+Treebank+for+Dutch%2E+Association+for+Computational+Linguistic)
24. Chun, Jayeol and Han, Na-Rae and Hwang, Jena D. and Choi, Jinho D. 2018. Building Universal Dependency Treebanks in Korean. European Language Resources Association (ELRA). [find](https://scholar.google.com/scholar?q=Chun%2C+Jayeol+and+Han%2C+Na%2DRae+and+Hwang%2C+Jena+D%2E+and+Choi%2C+Jinho+D%2E+2018%2E+Building+Universal+Dependency+Treebanks+in+Korean%2E+European+Language+Resources+Association+%28ELRA%29%2E)
25. Verginica Barbu Mititelu. 2018. Modern Syntactic Analysis of Romanian. Publishing House of "Alexandru Ioan Cuza" University. [find](https://scholar.google.com/scholar?q=Verginica+Barbu+Mititelu%2E+2018%2E+Modern+Syntactic+Analysis+of+Romanian%2E+Publishing+House+of+%22Alexandru+Ioan+Cuza%22+University%2E)
26. Dobrovoljc, Kaja and Erjavec, Tomaž and Krek, Simon. 2017. The Universal Dependencies Treebank for Slovenian. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Dobrovoljc%2C+Kaja+and+Erjavec%2C+Toma%C5%BE+and+Krek%2C+Simon%2E+2017%2E+The+Universal+Dependencies+Treebank+for+Slovenian%2E+Association+for+Computational+Linguistics%2E)
27. Muischnek, Kadri and Müürisep, Kaili and Puolakainen, Tiina. 2016. Estonian Dependency Treebank: from Constraint Grammar tagset to Universal Dependencies. European Language Resources Association (ELRA). [find](https://scholar.google.com/scholar?q=Muischnek%2C+Kadri+and+M%C3%BC%C3%BCrisep%2C+Kaili+and+Puolakainen%2C+Tiina%2E+2016%2E+Estonian+Dependency+Treebank%3A+from+Constraint+Grammar+tagset+to+Universal+Dependencies%2E+European+Language+Resources+Association+%28ELRA)
28. Kira Droganova and Olga Lyashevskaya and Daniel Zeman. 2018. Data Conversion and Consistency of Monolingual Corpora: Russian UD Treebanks. Linköping University Electronic Press. [find](https://scholar.google.com/scholar?q=Kira+Droganova+and+Olga+Lyashevskaya+and+Daniel+Zeman%2E+2018%2E+Data+Conversion+and+Consistency+of+Monolingual+Corpora%3A+Russian+UD+Treebanks%2E+Link%C3%B6ping+University+Electronic+Press%2E)
29. Nivre, Joakim and Megyesi, Beáta. 2007. Bootstrapping a Swedish Treebank Using Cross-Corpus Harmonization and Annotation Projection. [find](https://scholar.google.com/scholar?q=Nivre%2C+Joakim+and+Megyesi%2C+Be%C3%A1ta%2E+2007%2E+Bootstrapping+a+Swedish+Treebank+Using+Cross%2DCorpus+Harmonization+and+Annotation+Projection%2E)
30. Guillaume, Bruno and de Marneffe, Marie-Catherine and Perrier, Guy. 2019. Conversion et améliorations de corpus du français annotés en Universal Dependencies [Conversion and Improvement of Universal Dependencies French corpora]. ATALA (Association pour le Traitement Automatique des Langues). [find](https://scholar.google.com/scholar?q=Guillaume%2C+Bruno+and+de+Marneffe%2C+Marie%2DCatherine+and+Perrier%2C+Guy%2E+2019%2E+Conversion+et+am%C3%A9liorations+de+corpus+du+fran%C3%A7ais+annot%C3%A9s+en+Universal+Dependencies+%5BConversion+and+Improvement+of+Universal+D)
31. Petya Osenova and Kiril Simov. 2004. BTB-TR05: BulTreeBank Stylebook ą 05. [find](https://scholar.google.com/scholar?q=Petya+Osenova+and+Kiril+Simov%2E+2004%2E+BTB%2DTR05%3A+BulTreeBank+Stylebook+%C4%85+05%2E)
32. Hajič, Jan and Smrž, Otakar and Zemánek, Petr and Pajas, Petr and Šnaidauf, Jan and Beška, Emanuel and Kracmar, Jakub and Hassanová, Kamila. 2009. Prague Arabic Dependency Treebank 1.0. LINDAT/CLARIAH-CZ digital library at the Institute of Formal and Applied Linguistics (ÚFAL). [find](https://scholar.google.com/scholar?q=Haji%C4%8D%2C+Jan+and+Smr%C5%BE%2C+Otakar+and+Zem%C3%A1nek%2C+Petr+and+Pajas%2C+Petr+and+%C5%A0naidauf%2C+Jan+and+Be%C5%A1ka%2C+Emanuel+and+Kracmar%2C+Jakub+and+Hassanov%C3%A1%2C+Kamila%2E+2009%2E+Prague+Arabic+Dependency+Treebank+1%2E0%2E+LINDAT%2FCLARIAH)
33. Prokopidis, Prokopis and Papageorgiou, Haris. 2017. Universal Dependencies for Greek. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Prokopidis%2C+Prokopis+and+Papageorgiou%2C+Haris%2E+2017%2E+Universal+Dependencies+for+Greek%2E+Association+for+Computational+Linguistics%2E)
34. Pretkalniundefineda, Lauma and Rituma, Laura and Saulundefinedte, Baiba. 2018. Deriving Enhanced Universal Dependencies from a Hybrid Dependency-Constituency Treebank. Springer-Verlag. [find](https://scholar.google.com/scholar?q=Pretkalniundefineda%2C+Lauma+and+Rituma%2C+Laura+and+Saulundefinedte%2C+Baiba%2E+2018%2E+Deriving+Enhanced+Universal+Dependencies+from+a+Hybrid+Dependency%2DConstituency+Treebank%2E+Springer%2DVerlag%2E)
35. Shishkina, Yana and Lyashevskaya, Olga. 2021. Sculpting Enhanced Dependencies for Belarusian. Springer-Verlag. [find](https://scholar.google.com/scholar?q=Shishkina%2C+Yana+and+Lyashevskaya%2C+Olga%2E+2021%2E+Sculpting+Enhanced+Dependencies+for+Belarusian%2E+Springer%2DVerlag%2E)
36. Natalia Silveira and Timothy Dozat and Marie-Catherine de Marneffe and Samuel Bowman and Miriam Connor and John Bauer and Christopher D. Manning. 2014. A Gold Standard Dependency Corpus for English. [find](https://scholar.google.com/scholar?q=Natalia+Silveira+and+Timothy+Dozat+and+Marie%2DCatherine+de+Marneffe+and+Samuel+Bowman+and+Miriam+Connor+and+John+Bauer+and+Christopher+D%2E+Manning%2E+2014%2E+A+Gold+Standard+Dependency+Corpus+for+English%2E)
37. A.2. The specifications of LLMs used in the experiments are shown in Table 6. B. [find](https://scholar.google.com/scholar?q=A%2E2%2E+The+specifications+of+LLMs+used+in+the+experiments+are+shown+in+Table+6%2E+B%2E)
38. Taulé, Mariona and Martí, M. Antònia and Recasens, Marta. 2008. AnCora: Multilevel Annotated Corpora for Catalan and Spanish. European Language Resources Association (ELRA). [find](https://scholar.google.com/scholar?q=Taul%C3%A9%2C+Mariona+and+Mart%C3%AD%2C+M%2E+Ant%C3%B2nia+and+Recasens%2C+Marta%2E+2008%2E+AnCora%3A+Multilevel+Annotated+Corpora+for+Catalan+and+Spanish%2E+European+Language+Resources+Association+%28ELRA%29%2E)
39. Zeman, Daniel. 2017. Slovak Dependency Treebank in Universal Dependencies. [find](https://scholar.google.com/scholar?q=Zeman%2C+Daniel%2E+2017%2E+Slovak+Dependency+Treebank+in+Universal+Dependencies%2E)
40. A.1. Settings Environment and Hyper-parameters The environment and the hyper-parameters used in the experiments are shown in Table 4 and 5, respectively. Hardware GPU CPU RAM SSD Software OS CUDA Python PyTorch Transformers TRL PEFT vLLM Comparison between 3-step and 2-step-no-form prompts The detai… [find](https://scholar.google.com/scholar?q=A%2E1%2E+Settings+Environment+and+Hyper%2Dparameters+The+environment+and+the+hyper%2Dparameters+used+in+the+experiments+are+shown+in+Table+4+and+5%2C+respectively%2E+Hardware+GPU+CPU+RAM+SSD+Software+OS+CUDA+Pyth)
41. Wróblewska, Alina. 2018. Extended and Enhanced Polish Dependency Bank in Universal Dependencies Format. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Wr%C3%B3blewska%2C+Alina%2E+2018%2E+Extended+and+Enhanced+Polish+Dependency+Bank+in+Universal+Dependencies+Format%2E+Association+for+Computational+Linguistics%2E)