---
title: "Language Models Learn Constructional — Scivetti 2026"
description: "The paper asks whether open-source language models, and not only the largest prompted LLMs, understand both the form and the meaning of rare English…"
authors: ["Wesley Scivetti", "Ethan Gotlieb Wilcox", "Nathan Schneider", "Kanishka Misra", "Leonie Weissweiler"]
year: 2026
venue: "Proceedings of the 30th Conference on Computational Natural Language Learning"
source: "https://aclanthology.org/2026.conll-main.15/"
doi: "10.18653/v1/2026.conll-main.15"
licence: "CC BY 4.0 (ACL Anthology)"
licence_url: "https://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/scivetti-2026-language-models-learn-constructional-semantics/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/scivetti-2026-language-models-learn-constructional-semantics/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2026](https://md.research.elamur.ai/free/en/papers/2026/page/6/) / Language Models Learn Constructional Semantics, Not To Mention Syntax: Investigating LM Understanding of Paired-Focus Constructions

# Language Models Learn Constructional Semantics, Not To Mention Syntax: Investigating LM Understanding of Paired-Focus Constructions

**Authors:** [Wesley Scivetti](https://md.research.elamur.ai/free/en/authors/wesley-scivetti/), Ethan Gotlieb Wilcox, [Nathan Schneider](https://md.research.elamur.ai/free/en/authors/nathan-schneider/), [Kanishka Misra](https://md.research.elamur.ai/free/en/authors/kanishka-misra/), [Leonie Weissweiler](https://md.research.elamur.ai/free/en/authors/leonie-weissweiler/) · **Year:** 2026 · **Venue:** Proceedings of the 30th Conference on Computational Natural Language Learning · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2026.conll-main.15/) · [PDF](https://aclanthology.org/2026.conll-main.15.pdf) · [DOI 10.18653/v1/2026.conll-main.15](https://doi.org/10.18653/v1/2026.conll-main.15) · [OpenAlex](https://openalex.org/W7166841628)

**Citations:** 1 citations (openalex-snapshot · 2026-10-14)

## Summary
The paper asks whether open-source language models, and not only the largest prompted LLMs, understand both the form and the meaning of rare English PAIRED-FOCUS constructions: LET-ALONE, MUCH-LESS, NOT-TO-MENTION and NEVER-MIND. In these constructions, two focused elements sit on an implied scale, for example in a sentence saying someone was unable to pick up a small stone, let alone a big one.

The authors built a new evaluation set from scalar adjectives and everyday world knowledge. Each item pairs a construction sentence with a follow-up sentence that is either entailed or contradicted. Plausibility is varied so that constructional inference can be separated from typicality. They score raw model probabilities across many models that differ in size, architecture and training data. They also track open checkpoints during pretraining.

Models of roughly 400M parameters and larger, both encoders and decoders, capture the constructions' meaning. Models trained on human-scale data (BabyLM) never exceed chance on the semantic tests, even though they handle the syntax. Across training, form is learned first and meaning much later. The semantic learning curve tracks world-knowledge gains rather than grammatical ones. This weakens the case for text-only LMs as models of joint form–meaning acquisition.

## Key points
- Scales and adjectives come from Wilkinson and Tim (2016). Construction frequencies were counted with infini-gram in Olmo3 data and The Pile (Pythia), and checked against COCA. Hand-checked samples showed that 100% of LET-ALONE strings in COCA are true instances, but only 31–44% for the other three constructions.
- Syntactic knowledge plateaus early in training, similar to BLiMP curves. Semantic knowledge emerges later and follows the EWoK world-knowledge benchmark.
- Early in training, and in weaker models, predictions rely on typicality rather than constructional meaning.
- Results for the four constructions are strongly correlated with one another in both syntax and semantics.
- Pythia-12b is stable and robust to implausible follow-up sentences. The smaller Ettin models show unstable learning curves and perform worse on implausible items. Code and data are released at github.com/WesScivetti/Meaning_Alone.

*Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.*

Fields: [Linguistics & languages](https://md.research.elamur.ai/free/en/shelves/linguistics/)

## Cite

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@inproceedings{scivetti2026language,
  title = {{Language Models Learn Constructional Semantics, Not To Mention Syntax: Investigating LM Understanding of Paired-Focus Constructions}},
  author = {Scivetti, Wesley and Wilcox, Ethan Gotlieb and Schneider, Nathan and Misra, Kanishka and Weissweiler, Leonie},
  booktitle = {Proceedings of the 30th Conference on Computational Natural Language Learning},
  year = {2026},
  doi = {10.18653/v1/2026.conll-main.15},
  url = {https://doi.org/10.18653/v1/2026.conll-main.15}
}
```

- [← previous Language Models for the Restoration of Latin Legal Manuscripts](https://md.research.elamur.ai/free/en/papers/zhang-2026-language-models-restoration-latin-legal/)
- [next → Large Language Models Are Good Term Extractors: A Systematic Evaluation](https://md.research.elamur.ai/free/en/papers/terryn-2026-large-language-models-are-good/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/6/)

## References

63 references, 7 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Katrien Beuls and Paul Van Eecke. 2024. Humans learn language from situated communicative interactions. what about machines? Computational Linguistics, 50(4):1277–1311. [find](https://scholar.google.com/scholar?q=Katrien+Beuls+and+Paul+Van+Eecke%2E+2024%2E+Humans+learn+language+from+situated+communicative+interactions%2E+what+about+machines%3F+Computational+Linguistics%2C+50%284%29%3A1277%E2%80%931311%2E)
2. Stella Biderman, Hailey Schoelkopf, Quentin Gregory Anthony, Herbie Bradley, Kyle O’Brien, Eric Hallahan, Mohammad Aflah Khan, Shivanshu Purohit, Usvsn Sai Prashanth, Edward Raff, Aviya Skowron, Lintang Sutawika, and Oskar Van Der Wal. 2023. Pythia: A suite for analyzing large language models across… [find](https://scholar.google.com/scholar?q=Stella+Biderman%2C+Hailey+Schoelkopf%2C+Quentin+Gregory+Anthony%2C+Herbie+Bradley%2C+Kyle+O%E2%80%99Brien%2C+Eric+Hallahan%2C+Mohammad+Aflah+Khan%2C+Shivanshu+Purohit%2C+Usvsn+Sai+Prashanth%2C+Edward+Raff%2C+Aviya+Skowron%2C+Linta)
3. Claire Bonial and Harish Tayyar Madabushi. 2024. A construction grammar corpus of varying schematicity: A dataset for the evaluation of abstractions in language models. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COL… [find](https://scholar.google.com/scholar?q=Claire+Bonial+and+Harish+Tayyar+Madabushi%2E+2024%2E+A+construction+grammar+corpus+of+varying+schematicity%3A+A+dataset+for+the+evaluation+of+abstractions+in+language+models%2E+In+Proceedings+of+the+2024+Join)
4. Jérôme Botoko Ekila, Lara Verheyen, Katrien Beuls, and Paul Van Eecke. 2025. Constructions all the way up: From sensory experiences to construction grammars. In Proceedings of the Second International Workshop on Construction Grammars and NLP, pages 84–95, Düsseldorf, Germany. Association for Comput… [find](https://scholar.google.com/scholar?q=J%C3%A9r%C3%B4me+Botoko+Ekila%2C+Lara+Verheyen%2C+Katrien+Beuls%2C+and+Paul+Van+Eecke%2E+2025%2E+Constructions+all+the+way+up%3A+From+sensory+experiences+to+construction+grammars%2E+In+Proceedings+of+the+Second+International)
5. Bastian Bunzeck, Daniel Duran, and Sina Zarrieß. 2025. Do construction distributions shape formal language learning in german babylms? In Proceedings of the 29th Conference on Computational Natural Language Learning, pages 169–186, Vienna, Austria. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Bastian+Bunzeck%2C+Daniel+Duran%2C+and+Sina+Zarrie%C3%9F%2E+2025%2E+Do+construction+distributions+shape+formal+language+learning+in+german+babylms%3F+In+Proceedings+of+the+29th+Conference+on+Computational+Natural+La)
6. Gabriella Chronis, Kyle Mahowald, and Katrin Erk. 2023. A method for studying semantic construal in grammatical constructions with interpretable contextual embedding spaces. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 242–… [find](https://scholar.google.com/scholar?q=Gabriella+Chronis%2C+Kyle+Mahowald%2C+and+Katrin+Erk%2E+2023%2E+A+method+for+studying+semantic+construal+in+grammatical+constructions+with+interpretable+contextual+embedding+spaces%2E+In+Proceedings+of+the+61st)
7. Anne Cocos, Skyler Wharton, Ellie Pavlick, Marianna Apidianaki, and Chris Callison-Burch. 2018. Learning scalar adjective intensity from paraphrases. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 1752–1762, Brussels, Belgium. Association for Computa… [find](https://scholar.google.com/scholar?q=Anne+Cocos%2C+Skyler+Wharton%2C+Ellie+Pavlick%2C+Marianna+Apidianaki%2C+and+Chris+Callison%2DBurch%2E+2018%2E+Learning+scalar+adjective+intensity+from+paraphrases%2E+In+Proceedings+of+the+2018+Conference+on+Empirical) [our card](https://md.research.elamur.ai/free/en/papers/cocos-2018-learning-scalar-adjective-intensity-paraphrases/)
8. William Croft. 2001. Radical Construction Grammar: Syntactic Theory in Typological Perspective. Oxford University Press. [find](https://scholar.google.com/scholar?q=William+Croft%2E+2001%2E+Radical+Construction+Grammar%3A+Syntactic+Theory+in+Typological+Perspective%2E+Oxford+University+Press%2E)
9. Gerard de Melo and Mohit Bansal. 2013. Good, great, excellent: Global inference of semantic intensities. Transactions of the Association for Computational Linguistics, 1:279–290. [find](https://scholar.google.com/scholar?q=Gerard+de+Melo+and+Mohit+Bansal%2E+2013%2E+Good%2C+great%2C+excellent%3A+Global+inference+of+semantic+intensities%2E+Transactions+of+the+Association+for+Computational+Linguistics%2C+1%3A279%E2%80%93290%2E)
10. Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. BERT: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies,… [find](https://scholar.google.com/scholar?q=Jacob+Devlin%2C+Ming%2DWei+Chang%2C+Kenton+Lee%2C+and+Kristina+Toutanova%2E+2019%2E+BERT%3A+Pre%2Dtraining+of+deep+bidirectional+transformers+for+language+understanding%2E+In+Proceedings+of+the+2019+Conference+of+the+N)
11. Jonathan Dunn. 2017. Computational learning of construction grammars. Language and Cognition, 9(2):254–292. [find](https://scholar.google.com/scholar?q=Jonathan+Dunn%2E+2017%2E+Computational+learning+of+construction+grammars%2E+Language+and+Cognition%2C+9%282%29%3A254%E2%80%93292%2E)
12. Charles J. Fillmore, Paul Kay, and Mary Catherine O’Connor. 1988. Regularity and idiomaticity in grammatical constructions: The case of let alone. Language, 64(3):501–538. Publisher: Linguistic Society of America. [find](https://scholar.google.com/scholar?q=Charles+J%2E+Fillmore%2C+Paul+Kay%2C+and+Mary+Catherine+O%E2%80%99Connor%2E+1988%2E+Regularity+and+idiomaticity+in+grammatical+constructions%3A+The+case+of+let+alone%2E+Language%2C+64%283%29%3A501%E2%80%93538%2E+Publisher%3A+Linguistic+Societ)
13. Richard Futrell and Kyle Mahowald. 2025. How linguistics learned to stop worrying and love the language models. Behavioral and Brain Sciences, page 1–98. [find](https://scholar.google.com/scholar?q=Richard+Futrell+and+Kyle+Mahowald%2E+2025%2E+How+linguistics+learned+to+stop+worrying+and+love+the+language+models%2E+Behavioral+and+Brain+Sciences%2C+page+1%E2%80%9398%2E)
14. Aina Garí Soler and Marianna Apidianaki. 2020. BERT knows Punta Cana is not just beautiful, it’s gorgeous: Ranking scalar adjectives with contextualised representations. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 7371–7385, Online. Associ… [find](https://scholar.google.com/scholar?q=Aina+Gar%C3%AD+Soler+and+Marianna+Apidianaki%2E+2020%2E+BERT+knows+Punta+Cana+is+not+just+beautiful%2C+it%E2%80%99s+gorgeous%3A+Ranking+scalar+adjectives+with+contextualised+representations%2E+In+Proceedings+of+the+2020+Con)
15. Adele E. Goldberg. 1995. Constructions: A Construction Grammar Approach to Argument Structure. University of Chicago Press. [find](https://scholar.google.com/scholar?q=Adele+E%2E+Goldberg%2E+1995%2E+Constructions%3A+A+Construction+Grammar+Approach+to+Argument+Structure%2E+University+of+Chicago+Press%2E)
16. Adele E. Goldberg. 2006. Constructions at Work: The Nature of Generalization in Language. Oxford University Press. [find](https://scholar.google.com/scholar?q=Adele+E%2E+Goldberg%2E+2006%2E+Constructions+at+Work%3A+The+Nature+of+Generalization+in+Language%2E+Oxford+University+Press%2E)
17. Adele E. Goldberg. 2024. Usage-based constructionist approaches and large language models. Constructions and Frames, 16(2):220–254. [find](https://scholar.google.com/scholar?q=Adele+E%2E+Goldberg%2E+2024%2E+Usage%2Dbased+constructionist+approaches+and+large+language+models%2E+Constructions+and+Frames%2C+16%282%29%3A220%E2%80%93254%2E)
18. Jennifer Hu, Jon Gauthier, Peng Qian, Ethan Wilcox, and Roger Levy. 2020. A systematic assessment of syntactic generalization in neural language models. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 1725–1744, Online. Association for Computational… [find](https://scholar.google.com/scholar?q=Jennifer+Hu%2C+Jon+Gauthier%2C+Peng+Qian%2C+Ethan+Wilcox%2C+and+Roger+Levy%2E+2020%2E+A+systematic+assessment+of+syntactic+generalization+in+neural+language+models%2E+In+Proceedings+of+the+58th+Annual+Meeting+of+th)
19. Michael Y. Hu, Aaron Mueller, Candace Ross, Adina Williams, Tal Linzen, Chengxu Zhuang, Ryan Cotterell, Leshem Choshen, Alex Warstadt, and Ethan Gotlieb Wilcox. 2024. Findings of the second BabyLM challenge: Sample-efficient pretraining on developmentally plausible corpora. In The 2nd BabyLM Challen… [find](https://scholar.google.com/scholar?q=Michael+Y%2E+Hu%2C+Aaron+Mueller%2C+Candace+Ross%2C+Adina+Williams%2C+Tal+Linzen%2C+Chengxu+Zhuang%2C+Ryan+Cotterell%2C+Leshem+Choshen%2C+Alex+Warstadt%2C+and+Ethan+Gotlieb+Wilcox%2E+2024%2E+Findings+of+the+second+BabyLM+cha)
20. Xinyao Huang, Yue Pan, Stefan Hartmann, and Yang Yanning. 2025. Assessing minimal pairs of Chinese verb-resultative complement constructions: Insights from language models. In Proceedings of the Second International Workshop on Construction Grammars and NLP, pages 144–150, Düsseldorf, Germany. Assoc… [find](https://scholar.google.com/scholar?q=Xinyao+Huang%2C+Yue+Pan%2C+Stefan+Hartmann%2C+and+Yang+Yanning%2E+2025%2E+Assessing+minimal+pairs+of+Chinese+verb%2Dresultative+complement+constructions%3A+Insights+from+language+models%2E+In+Proceedings+of+the+Secon)
21. Anna A. Ivanova, Aalok Sathe, Benjamin Lipkin, Un-nathi U. Kumar, Setayesh Radkani, Thomas H. Clark, Carina Kauf, Jennifer Hu, R. T. Pramod, Gabriel Grand, Vivian C. Paulun, Maria Ryskina, Ekin Akyürek, Ethan G. Wilcox, Nafisa Rashid, Leshem Choshen, Roger Levy, Evelina Fedorenko, Joshua Tenenbaum,… [find](https://scholar.google.com/scholar?q=Anna+A%2E+Ivanova%2C+Aalok+Sathe%2C+Benjamin+Lipkin%2C+Un%2Dnathi+U%2E+Kumar%2C+Setayesh+Radkani%2C+Thomas+H%2E+Clark%2C+Carina+Kauf%2C+Jennifer+Hu%2C+R%2E+T%2E+Pramod%2C+Gabriel+Grand%2C+Vivian+C%2E+Paulun%2C+Maria+Ryskina%2C+Ekin+Aky%C3%BCre)
22. Carina Kauf and Anna A. Ivanova. 2023. A better way to do masked language model scoring. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 925–935, Toronto, Canada. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Carina+Kauf+and+Anna+A%2E+Ivanova%2E+2023%2E+A+better+way+to+do+masked+language+model+scoring%2E+In+Proceedings+of+the+61st+Annual+Meeting+of+the+Association+for+Computational+Linguistics+%28Volume+2%3A+Short+Pap)
23. Bai Li, Zining Zhu, Guillaume Thomas, Frank Rudzicz, and Yang Xu. 2022. Neural reality of argument structure constructions. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), page 7410–7423, Dublin, Ireland. Association for Computation… [find](https://scholar.google.com/scholar?q=Bai+Li%2C+Zining+Zhu%2C+Guillaume+Thomas%2C+Frank+Rudzicz%2C+and+Yang+Xu%2E+2022%2E+Neural+reality+of+argument+structure+constructions%2E+In+Proceedings+of+the+60th+Annual+Meeting+of+the+Association+for+Computation)
24. Fangru Lin, Daniel Altshuler, and Janet B. Pierrehumbert. 2024. Probing large language models for scalar adjective lexical semantics and scalar diversity pragmatics. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING… [find](https://scholar.google.com/scholar?q=Fangru+Lin%2C+Daniel+Altshuler%2C+and+Janet+B%2E+Pierrehumbert%2E+2024%2E+Probing+large+language+models+for+scalar+adjective+lexical+semantics+and+scalar+diversity+pragmatics%2E+In+Proceedings+of+the+2024+Joint+I)
25. Jiacheng Liu, Sewon Min, Luke Zettlemoyer, Yejin Choi, and Hannaneh Hajishirzi. 2024. Infini-gram: Scaling unbounded n-gram language models to a trillion tokens. In Proceedings of the First Conference on Language Modeling. [find](https://scholar.google.com/scholar?q=Jiacheng+Liu%2C+Sewon+Min%2C+Luke+Zettlemoyer%2C+Yejin+Choi%2C+and+Hannaneh+Hajishirzi%2E+2024%2E+Infini%2Dgram%3A+Scaling+unbounded+n%2Dgram+language+models+to+a+trillion+tokens%2E+In+Proceedings+of+the+First+Conference)
26. Yinhan Liu, Myle Ott, Naman Goyal, Jingfei Du, Mandar Joshi, Danqi Chen, Omer Levy, Mike Lewis, Luke Zettlemoyer, and Veselin Stoyanov. 2019. Roberta: A robustly optimized bert pretraining approach. Preprint, arXiv:1907.11692. [find](https://scholar.google.com/scholar?q=Yinhan+Liu%2C+Myle+Ott%2C+Naman+Goyal%2C+Jingfei+Du%2C+Mandar+Joshi%2C+Danqi+Chen%2C+Omer+Levy%2C+Mike+Lewis%2C+Luke+Zettlemoyer%2C+and+Veselin+Stoyanov%2E+2019%2E+Roberta%3A+A+robustly+optimized+bert+pretraining+approach%2E+P)
27. Isabelle Lorge and Janet B. Pierrehumbert. 2023. Not wacky vs. definitely wacky: A study of scalar adverbs in pretrained language models. In Proceedings of the 6th BlackboxNLP Workshop: Analyzing and Interpreting Neural Networks for NLP, pages 296–316, Singapore. Association for Computational Lingui… [find](https://scholar.google.com/scholar?q=Isabelle+Lorge+and+Janet+B%2E+Pierrehumbert%2E+2023%2E+Not+wacky+vs%2E+definitely+wacky%3A+A+study+of+scalar+adverbs+in+pretrained+language+models%2E+In+Proceedings+of+the+6th+BlackboxNLP+Workshop%3A+Analyzing+and+)
28. Kyle Mahowald. 2023. A discerning several thousand judgments: GPT-3 rates the article + adjective + numeral + noun construction. In Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics, pages 265– 273, Dubrovnik, Croatia. Association for Computa… [find](https://scholar.google.com/scholar?q=Kyle+Mahowald%2E+2023%2E+A+discerning+several+thousand+judgments%3A+GPT%2D3+rates+the+article+%2B+adjective+%2B+numeral+%2B+noun+construction%2E+In+Proceedings+of+the+17th+Conference+of+the+European+Chapter+of+the+As)
29. Kanishka Misra and Kyle Mahowald. 2024. Language models learn rare phenomena from less rare phenomena: The case of the missing AANNs. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 913–929, Miami, Florida, USA. Association for Computational Linguisti… [find](https://scholar.google.com/scholar?q=Kanishka+Misra+and+Kyle+Mahowald%2E+2024%2E+Language+models+learn+rare+phenomena+from+less+rare+phenomena%3A+The+case+of+the+missing+AANNs%2E+In+Proceedings+of+the+2024+Conference+on+Empirical+Methods+in+Natu)
30. Kanishka Misra, Julia Rayz, and Allyson Ettinger. 2023. COMPS: Conceptual minimal pair sentences for testing robust property knowledge and its inheritance in pre-trained language models. In Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics, p… [find](https://scholar.google.com/scholar?q=Kanishka+Misra%2C+Julia+Rayz%2C+and+Allyson+Ettinger%2E+2023%2E+COMPS%3A+Conceptual+minimal+pair+sentences+for+testing+robust+property+knowledge+and+its+inheritance+in+pre%2Dtrained+language+models%2E+In+Proceeding)
31. David R. Mortensen, Valentina Izrailevitch, Yunze Xiao, Hinrich Schütze, and Leonie Weissweiler. 2024. Verbing weirds language (models): Evaluation of English zero-derivation in five LLMs. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and… [find](https://scholar.google.com/scholar?q=David+R%2E+Mortensen%2C+Valentina+Izrailevitch%2C+Yunze+Xiao%2C+Hinrich+Sch%C3%BCtze%2C+and+Leonie+Weissweiler%2E+2024%2E+Verbing+weirds+language+%28models%29%3A+Evaluation+of+English+zero%2Dderivation+in+five+LLMs%2E+In+Proceedi)
32. Rashid Nizamani, Sebastian Schuster, and Vera Demberg. 2024. SIGA: A naturalistic NLI dataset of English scalar implicatures with gradable adjectives. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 1… [find](https://scholar.google.com/scholar?q=Rashid+Nizamani%2C+Sebastian+Schuster%2C+and+Vera+Demberg%2E+2024%2E+SIGA%3A+A+naturalistic+NLI+dataset+of+English+scalar+implicatures+with+gradable+adjectives%2E+In+Proceedings+of+the+2024+Joint+International+Co) [our card](https://md.research.elamur.ai/free/en/papers/nizamani-2024-siga-naturalistic-nli-dataset-english/)
33. Team Olmo, Allyson Ettinger, Amanda Bertsch, Bailey Kuehl, David Graham, David Heineman, Dirk Groeneveld, Faeze Brahman, Finbarr Timbers, Hamish Ivison, Jacob Morrison, Jake Poznanski, Kyle Lo, Luca Soldaini, Matt Jordan, Mayee Chen, Michael Noukhovitch, Nathan Lambert, Pete Walsh, and 49 others. 20… [find](https://scholar.google.com/scholar?q=Team+Olmo%2C+Allyson+Ettinger%2C+Amanda+Bertsch%2C+Bailey+Kuehl%2C+David+Graham%2C+David+Heineman%2C+Dirk+Groeneveld%2C+Faeze+Brahman%2C+Finbarr+Timbers%2C+Hamish+Ivison%2C+Jacob+Morrison%2C+Jake+Poznanski%2C+Kyle+Lo%2C+Luca+S) [our card](https://md.research.elamur.ai/free/en/papers/ettinger-2025-olmo-3/)
34. Team OLMo, Pete Walsh, Luca Soldaini, Dirk Groeneveld, Kyle Lo, Shane Arora, Akshita Bhagia, Yuling Gu, Shengyi Huang, Matt Jordan, Nathan Lambert, Dustin Schwenk, Oyvind Tafjord, Taira Anderson, David Atkinson, Faeze Brahman, Christopher Clark, Pradeep Dasigi, Nouha Dziri, and 24 others. 2025. 2 ol… [find](https://scholar.google.com/scholar?q=Team+OLMo%2C+Pete+Walsh%2C+Luca+Soldaini%2C+Dirk+Groeneveld%2C+Kyle+Lo%2C+Shane+Arora%2C+Akshita+Bhagia%2C+Yuling+Gu%2C+Shengyi+Huang%2C+Matt+Jordan%2C+Nathan+Lambert%2C+Dustin+Schwenk%2C+Oyvind+Tafjord%2C+Taira+Anderson%2C+Davi)
35. Steven Piantadosi. 2024. Modern language models refute Chomsky’s approach to language, page 353–414. Language Sciences Press, Berlin, Germany. [find](https://scholar.google.com/scholar?q=Steven+Piantadosi%2E+2024%2E+Modern+language+models+refute+Chomsky%E2%80%99s+approach+to+language%2C+page+353%E2%80%93414%2E+Language+Sciences+Press%2C+Berlin%2C+Germany%2E)
36. Christopher Potts. 2024. Characterizing English preposing in PP constructions. Journal of Linguistics, page 1–39. [find](https://scholar.google.com/scholar?q=Christopher+Potts%2E+2024%2E+Characterizing+English+preposing+in+PP+constructions%2E+Journal+of+Linguistics%2C+page+1%E2%80%9339%2E)
37. Alec Radford, Jeffrey Wu, Rewon Child, David Luan, Dario Amodei, and Ilya Sutskever. 2019. Language models are unsupervised multitask learners. Technical report, OpenAI. [find](https://scholar.google.com/scholar?q=Alec+Radford%2C+Jeffrey+Wu%2C+Rewon+Child%2C+David+Luan%2C+Dario+Amodei%2C+and+Ilya+Sutskever%2E+2019%2E+Language+models+are+unsupervised+multitask+learners%2E+Technical+report%2C+OpenAI%2E)
38. Joshua Rozner, Leonie Weissweiler, Kyle Mahowald, and Cory Shain. 2025a. Constructions are revealed in word distributions. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pages 2116–2138, Suzhou, China. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Joshua+Rozner%2C+Leonie+Weissweiler%2C+Kyle+Mahowald%2C+and+Cory+Shain%2E+2025a%2E+Constructions+are+revealed+in+word+distributions%2E+In+Proceedings+of+the+2025+Conference+on+Empirical+Methods+in+Natural+Languag)
39. Joshua Rozner, Leonie Weissweiler, and Cory Shain. 2025b. BabyLM’s first constructions: Causal interventions provide a signal of learning. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pages 2237–2249, Suzhou, China. Association for Computational Linguist… [find](https://scholar.google.com/scholar?q=Joshua+Rozner%2C+Leonie+Weissweiler%2C+and+Cory+Shain%2E+2025b%2E+BabyLM%E2%80%99s+first+constructions%3A+Causal+interventions+provide+a+signal+of+learning%2E+In+Proceedings+of+the+2025+Conference+on+Empirical+Methods+in)
40. Julian Salazar, Davis Liang, Toan Q. Nguyen, and Katrin Kirchhoff. 2020. Masked language model scoring. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 2699–2712, Online. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Julian+Salazar%2C+Davis+Liang%2C+Toan+Q%2E+Nguyen%2C+and+Katrin+Kirchhoff%2E+2020%2E+Masked+language+model+scoring%2E+In+Proceedings+of+the+58th+Annual+Meeting+of+the+Association+for+Computational+Linguistics%2C+page) [our card](https://md.research.elamur.ai/free/en/papers/salazar-2020-masked-language-model-scoring/)
41. Sebastian Schuster, Yuxing Chen, and Judith Degen. 2020. Harnessing the linguistic signal to predict scalar inferences. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 5387–5403, Online. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Sebastian+Schuster%2C+Yuxing+Chen%2C+and+Judith+Degen%2E+2020%2E+Harnessing+the+linguistic+signal+to+predict+scalar+inferences%2E+In+Proceedings+of+the+58th+Annual+Meeting+of+the+Association+for+Computational+L) [our card](https://md.research.elamur.ai/free/en/papers/schuster-2020-harnessing-linguistic-signal-predict-scalar/)
42. Wesley Scivetti, Tatsuya Aoyama, Ethan Wilcox, and Nathan Schneider. 2025a. Unpacking Let Alone: Human-scale models generalize to a rare construction in form but not meaning. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pages 27503–27514, Suzhou, China.… [find](https://scholar.google.com/scholar?q=Wesley+Scivetti%2C+Tatsuya+Aoyama%2C+Ethan+Wilcox%2C+and+Nathan+Schneider%2E+2025a%2E+Unpacking+Let+Alone%3A+Human%2Dscale+models+generalize+to+a+rare+construction+in+form+but+not+meaning%2E+In+Proceedings+of+the+202)
43. Wesley Scivetti and Nathan Schneider. 2025. Construction identification and disambiguation using BERT: A case study of NPN. In Proceedings of the 29th Conference on Computational Natural Language Learning, pages 365–376, Vienna, Austria. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Wesley+Scivetti+and+Nathan+Schneider%2E+2025%2E+Construction+identification+and+disambiguation+using+BERT%3A+A+case+study+of+NPN%2E+In+Proceedings+of+the+29th+Conference+on+Computational+Natural+Language+Lear)
44. Wesley Scivetti, Melissa Torgbi, Mollie Shichman, Taylor Pellegrin, Austin Blodgett, Claire Bonial, and Harish Tayyar Madabushi. 2025b. Beyond memorization: Assessing semantic generalization in large language models using phrasal constructions. In Proceedings of the 14th International Joint Conferen… [find](https://scholar.google.com/scholar?q=Wesley+Scivetti%2C+Melissa+Torgbi%2C+Mollie+Shichman%2C+Taylor+Pellegrin%2C+Austin+Blodgett%2C+Claire+Bonial%2C+and+Harish+Tayyar+Madabushi%2E+2025b%2E+Beyond+memorization%3A+Assessing+semantic+generalization+in+large+)
45. Thibault Sellam, Steve Yadlowsky, Ian Tenney, Jason Wei, Naomi Saphra, Alexander D’Amour, Tal Linzen, Jasmijn Bastings, Iulia Raluca Turc, Jacob Eisenstein, Dipanjan Das, and Ellie Pavlick. 2022. The multiB-ERTs: BERT reproductions for robustness analysis. In International Conference on Learning Rep… [find](https://scholar.google.com/scholar?q=Thibault+Sellam%2C+Steve+Yadlowsky%2C+Ian+Tenney%2C+Jason+Wei%2C+Naomi+Saphra%2C+Alexander+D%E2%80%99Amour%2C+Tal+Linzen%2C+Jasmijn+Bastings%2C+Iulia+Raluca+Turc%2C+Jacob+Eisenstein%2C+Dipanjan+Das%2C+and+Ellie+Pavlick%2E+2022%2E+The+)
46. Hakyung Sung and Kristopher Kyle. 2024. Leveraging pre-trained language models for linguistic analysis: A case of argument structure constructions. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 7302–7314, Miami, Florida, USA. Association for Computa… [find](https://scholar.google.com/scholar?q=Hakyung+Sung+and+Kristopher+Kyle%2E+2024%2E+Leveraging+pre%2Dtrained+language+models+for+linguistic+analysis%3A+A+case+of+argument+structure+constructions%2E+In+Proceedings+of+the+2024+Conference+on+Empirical+M)
47. Harish Tayyar Madabushi, Laurence Romain, Dagmar Divjak, and Petar Milin. 2020. CxGBERT: BERT meets Construction Grammar. In Proceedings of the 28th International Conference on Computational Linguistics, page 4020–4032, Barcelona, Spain (Online). International Committee on Computational Linguistics. [find](https://scholar.google.com/scholar?q=Harish+Tayyar+Madabushi%2C+Laurence+Romain%2C+Dagmar+Divjak%2C+and+Petar+Milin%2E+2020%2E+CxGBERT%3A+BERT+meets+Construction+Grammar%2E+In+Proceedings+of+the+28th+International+Conference+on+Computational+Linguisti)
48. Yu-Hsiang Tseng, Cing-Fang Shih, Pin-Er Chen, Hsin-Yu Chou, Mao-Chang Ku, and Shu-Kai Hsieh. 2022. CxLM: A construction and context-aware language model. In Proceedings of the Thirteenth Language Resources and Evaluation Conference, page 6361–6369, Marseille, France. European Language Resources Asso… [find](https://scholar.google.com/scholar?q=Yu%2DHsiang+Tseng%2C+Cing%2DFang+Shih%2C+Pin%2DEr+Chen%2C+Hsin%2DYu+Chou%2C+Mao%2DChang+Ku%2C+and+Shu%2DKai+Hsieh%2E+2022%2E+CxLM%3A+A+construction+and+context%2Daware+language+model%2E+In+Proceedings+of+the+Thirteenth+Language+Reso)
49. Tim Veenboer and Jelke Bloem. 2023. Using collostructional analysis to evaluate BERT’s representation of linguistic constructions. In Findings of the Association for Computational Linguistics: ACL 2023, page 12937–12951, Toronto, Canada. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Tim+Veenboer+and+Jelke+Bloem%2E+2023%2E+Using+collostructional+analysis+to+evaluate+BERT%E2%80%99s+representation+of+linguistic+constructions%2E+In+Findings+of+the+Association+for+Computational+Linguistics%3A+ACL+202)
50. Lara Verheyen, Jonas Doumen, Paul Van Eecke, and Katrien Beuls. 2025. You shall know a construction by the company it keeps: Computational construction grammar with embeddings. In Proceedings of the Second International Workshop on Construction Grammars and NLP, pages 75–83, Düsseldorf, Germany. Ass… [find](https://scholar.google.com/scholar?q=Lara+Verheyen%2C+Jonas+Doumen%2C+Paul+Van+Eecke%2C+and+Katrien+Beuls%2E+2025%2E+You+shall+know+a+construction+by+the+company+it+keeps%3A+Computational+construction+grammar+with+embeddings%2E+In+Proceedings+of+the+S)
51. Shengao Wang, Arjun Chandra, Aoming Liu, Venkatesh Saligrama, and Boqing Gong. 2025. Babyvlm: Data-efficient pretraining of vlms inspired by infant learning. In Proceedings of the IEEE/CVF International Conference on Computer Vision, page 1380–1390, Honolulu, Hawaii. [find](https://scholar.google.com/scholar?q=Shengao+Wang%2C+Arjun+Chandra%2C+Aoming+Liu%2C+Venkatesh+Saligrama%2C+and+Boqing+Gong%2E+2025%2E+Babyvlm%3A+Data%2Defficient+pretraining+of+vlms+inspired+by+infant+learning%2E+In+Proceedings+of+the+IEEE%2FCVF+Internation)
52. Benjamin Warner, Antoine Chaffin, Benjamin Clavié, Orion Weller, Oskar Hallström, Said Taghadouini, Alexis Gallagher, Raja Biswas, Faisal Ladhak, Tom Aarsen, Griffin Thomas Adams, Jeremy Howard, and Iacopo Poli. 2025. Smarter, better, faster, longer: A modern bidirectional encoder for fast, memory e… [find](https://scholar.google.com/scholar?q=Benjamin+Warner%2C+Antoine+Chaffin%2C+Benjamin+Clavi%C3%A9%2C+Orion+Weller%2C+Oskar+Hallstr%C3%B6m%2C+Said+Taghadouini%2C+Alexis+Gallagher%2C+Raja+Biswas%2C+Faisal+Ladhak%2C+Tom+Aarsen%2C+Griffin+Thomas+Adams%2C+Jeremy+Howard%2C+and+I) [our card](https://md.research.elamur.ai/free/en/papers/warner-2024-smarter-better-faster-longer-modern/)
53. Alex Warstadt and Samuel R Bowman. 2022. What artificial neural networks can tell us about human language Acquisition. In Algebraic structures in natural language, pages 17–60. CRC Press. [find](https://scholar.google.com/scholar?q=Alex+Warstadt+and+Samuel+R+Bowman%2E+2022%2E+What+artificial+neural+networks+can+tell+us+about+human+language+Acquisition%2E+In+Algebraic+structures+in+natural+language%2C+pages+17%E2%80%9360%2E+CRC+Press%2E)
54. Alex Warstadt, Aaron Mueller, Leshem Choshen, Ethan Wilcox, Chengxu Zhuang, Juan Ciro, Rafael Mosquera, Bhargavi Paranjabe, Adina Williams, Tal Linzen, and Ryan Cotterell. 2023. Findings of the BabyLM challenge: Sample-efficient pretraining on developmentally plausible corpora. In Proceedings of the… [find](https://scholar.google.com/scholar?q=Alex+Warstadt%2C+Aaron+Mueller%2C+Leshem+Choshen%2C+Ethan+Wilcox%2C+Chengxu+Zhuang%2C+Juan+Ciro%2C+Rafael+Mosquera%2C+Bhargavi+Paranjabe%2C+Adina+Williams%2C+Tal+Linzen%2C+and+Ryan+Cotterell%2E+2023%2E+Findings+of+the+BabyLM)
55. Alex Warstadt, Alicia Parrish, Haokun Liu, Anhad Mohananey, Wei Peng, Sheng-Fu Wang, and Samuel R. Bowman. 2020. BLiMP: The benchmark of linguistic minimal pairs for English. Transactions of the Association for Computational Linguistics, 8:377– 392. [find](https://scholar.google.com/scholar?q=Alex+Warstadt%2C+Alicia+Parrish%2C+Haokun+Liu%2C+Anhad+Mohananey%2C+Wei+Peng%2C+Sheng%2DFu+Wang%2C+and+Samuel+R%2E+Bowman%2E+2020%2E+BLiMP%3A+The+benchmark+of+linguistic+minimal+pairs+for+English%2E+Transactions+of+the+Assoc)
56. Leonie Weissweiler, Taiqi He, Naoki Otani, David R. Mortensen, Lori Levin, and Hinrich Schütze. 2023. Construction grammar provides unique insight into neural language models. In Proceedings of the First International Workshop on Construction Grammars and NLP (CxGs+NLP, GURT/SyntaxFest 2023), pages… [find](https://scholar.google.com/scholar?q=Leonie+Weissweiler%2C+Taiqi+He%2C+Naoki+Otani%2C+David+R%2E+Mortensen%2C+Lori+Levin%2C+and+Hinrich+Sch%C3%BCtze%2E+2023%2E+Construction+grammar+provides+unique+insight+into+neural+language+models%2E+In+Proceedings+of+the+Fi)
57. Leonie Weissweiler, Valentin Hofmann, Abdullatif Köksal, and Hinrich Schütze. 2022. The better your syntax, the better your semantics? Probing pretrained language models for the English Comparative Correlative. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing… [find](https://scholar.google.com/scholar?q=Leonie+Weissweiler%2C+Valentin+Hofmann%2C+Abdullatif+K%C3%B6ksal%2C+and+Hinrich+Sch%C3%BCtze%2E+2022%2E+The+better+your+syntax%2C+the+better+your+semantics%3F+Probing+pretrained+language+models+for+the+English+Comparative+Co)
58. Orion Weller, Kathryn Ricci, Marc Marone, Antoine Chaffin, Dawn Lawrie, and Benjamin Van Durme. 2025. Seq vs seq: An open suite of paired encoders and decoders. Preprint, arXiv:2507.11412. — [arXiv:2507.11412](https://arxiv.org/abs/2507.11412) [find](https://scholar.google.com/scholar?q=Orion+Weller%2C+Kathryn+Ricci%2C+Marc+Marone%2C+Antoine+Chaffin%2C+Dawn+Lawrie%2C+and+Benjamin+Van+Durme%2E+2025%2E+Seq+vs+seq%3A+An+open+suite+of+paired+encoders+and+decoders%2E+Preprint%2C+arXiv%3A2507%2E11412%2E+%E2%80%94+%5BarXiv%3A25)
59. Bryan Wilkinson and Oates Tim. 2016. A gold standard for scalar adjectives. In Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16), pages 2669–2675, Portorož, Slovenia. European Language Resources Association (ELRA). [find](https://scholar.google.com/scholar?q=Bryan+Wilkinson+and+Oates+Tim%2E+2016%2E+A+gold+standard+for+scalar+adjectives%2E+In+Proceedings+of+the+Tenth+International+Conference+on+Language+Resources+and+Evaluation+%28LREC%E2%80%9916%29%2C+pages+2669%E2%80%932675%2C+Portor) [our card](https://md.research.elamur.ai/free/en/papers/wilkinson-2016-gold-standard-scalar-adjectives/)
60. Xiulin Yang. 2025. Language models at the syntax-semantics interface: A case study of the long-distance binding of Chinese reflexive ziji. In Proceedings of the 31st International Conference on Computational Linguistics, pages 3808–3824, Abu Dhabi, UAE. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Xiulin+Yang%2E+2025%2E+Language+models+at+the+syntax%2Dsemantics+interface%3A+A+case+study+of+the+long%2Ddistance+binding+of+Chinese+reflexive+ziji%2E+In+Proceedings+of+the+31st+International+Conference+on+Comput)
61. Susan Zhang, Stephen Roller, Naman Goyal, Mikel Artetxe, Moya Chen, Shuohui Chen, Christopher Dewan, Mona Diab, Xian Li, Xi Victoria Lin, Todor Mihaylov, Myle Ott, Sam Shleifer, Kurt Shuster, Daniel Simig, Punit Singh Koura, Anjali Sridhar, Tianlu Wang, and Luke Zettlemoyer. 2022. OPT: Open Pre-trai… [find](https://scholar.google.com/scholar?q=Susan+Zhang%2C+Stephen+Roller%2C+Naman+Goyal%2C+Mikel+Artetxe%2C+Moya+Chen%2C+Shuohui+Chen%2C+Christopher+Dewan%2C+Mona+Diab%2C+Xian+Li%2C+Xi+Victoria+Lin%2C+Todor+Mihaylov%2C+Myle+Ott%2C+Sam+Shleifer%2C+Kurt+Shuster%2C+Daniel+S)
62. Shijia Zhou, Leonie Weissweiler, Taiqi He, Hinrich Schütze, David R. Mortensen, and Lori Levin. 2024. Constructions are so difficult that Even large language models get them right for the wrong reasons. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language… [find](https://scholar.google.com/scholar?q=Shijia+Zhou%2C+Leonie+Weissweiler%2C+Taiqi+He%2C+Hinrich+Sch%C3%BCtze%2C+David+R%2E+Mortensen%2C+and+Lori+Levin%2E+2024%2E+Constructions+are+so+difficult+that+Even+large+language+models+get+them+right+for+the+wrong+reason)
63. Daniel M. Ziegler, Nisan Stiennon, Jeffrey Wu, Tom B. Brown, Alec Radford, Dario Amodei, Paul Christiano, and Geoffrey Irving. 2020. Fine-tuning language models from human preferences. arXiv preprint. ArXiv:1909.08593 [cs]. [find](https://scholar.google.com/scholar?q=Daniel+M%2E+Ziegler%2C+Nisan+Stiennon%2C+Jeffrey+Wu%2C+Tom+B%2E+Brown%2C+Alec+Radford%2C+Dario+Amodei%2C+Paul+Christiano%2C+and+Geoffrey+Irving%2E+2020%2E+Fine%2Dtuning+language+models+from+human+preferences%2E+arXiv+preprint%2E)