---
title: "Biasless Language Models Learn Unnaturally: How LLMs Fail to"
description: "That claim was used to argue that human typology does not need strong innate biases. 48 references, cited by 3 papers here."
authors: ["Imry Ziv", "Nur Lan", "Emmanuel Chemla"]
year: 2026
venue: "Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)"
source: "https://aclanthology.org/2026.eacl-long.249/"
doi: "10.18653/v1/2026.eacl-long.249"
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/ziv-2026-biasless-language-models-learn-unnaturally/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/ziv-2026-biasless-language-models-learn-unnaturally/)

[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/5/) / Biasless Language Models Learn Unnaturally: How LLMs Fail to Distinguish the Possible from the Impossible

# Biasless Language Models Learn Unnaturally: How LLMs Fail to Distinguish the Possible from the Impossible

**Authors:** Imry Ziv, Nur Lan and [Emmanuel Chemla](https://md.research.elamur.ai/free/en/authors/emmanuel-chemla/) · **Year:** 2026 · **Venue:** [Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)](https://md.research.elamur.ai/free/en/venues/eacl/) ([EACL 2026](https://md.research.elamur.ai/free/en/venues/eacl/2026/)) · **Publisher:** [Association for Computational Linguistics](https://md.research.elamur.ai/free/en/publishers/association-for-computational-linguistics/) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2026.eacl-long.249/) · [PDF](https://aclanthology.org/2026.eacl-long.249.pdf) · [DOI 10.18653/v1/2026.eacl-long.249](https://doi.org/10.18653/v1/2026.eacl-long.249) · [OpenAlex](https://openalex.org/W4415097652)

**Citations:** 0 citations (OpenAlex, 2026-10-14) · [3](https://md.research.elamur.ai/free/en/papers/ziv-2026-biasless-language-models-learn-unnaturally/cited-by/) in our library, of the 149,439 papers whose bibliographies we read

## Summary
The paper asks whether large language models, like human learners, find naturally occurring languages easier to acquire than "impossible" ones that break core linguistic constraints such as hierarchical, recursive structure. Kallini et al. (2024) had claimed that GPT-2 shows this preference. That claim was used to argue that human typology does not need strong innate biases. The authors reuse that ease-of-learning setup and widen it to more languages and more perturbation functions, mostly sentence-level shuffles and reversals. They train GPT-2 on each original dataset and on its perturbed variants, then compare validation perplexity curves. They examine the data from two angles. Intralinguistically, they compare each language with its own impossible versions. Interlinguistically, they test whether the full set of attested languages separates from the full set of impossible ones. In most cases GPT-2 learned the impossible variant as easily as the original, and sometimes more easily. Neither perspective produced a systematic boundary. This weakens the case for LLMs as evidence against the generative hypothesis and raises doubts about using them as models of human linguistic cognition.

## Key points
- The study replicates and extends the Kallini et al. (2024) perplexity-curve method. Model: GPT-2. Example perturbations: SHUFFLE global and SHUFFLE local, which scramble word order within sentences.
- Two ease-of-learning metrics come from the learning curves: the minimum perplexity reached during training and the area under the perplexity curve (AUC).
- In the interlinguistic test, the authors compare variance across languages under the same perturbation with variance within a language across its perturbations. Successful separation would predict higher within-language variance, but the results showed the reverse: each language grouped with its own impossible variants.
- Setup differences from earlier work:
  - one whitespace tokenizer for all languages (vocabulary 50,257) rather than language-specific pretrained tokenizers;
  - no learning-rate warmup;
  - different training set sizes and hyperparameters.
- Acknowledged limitations:
  - only GPT-2 was tested;
  - the sets of languages and perturbations are limited;
  - learning asymmetries alone cannot fully account for typology.

  Training ran on the Jean Zay supercomputer (GENCI/IDRIS).

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

## Institutions

- [Tel Aviv University](https://md.research.elamur.ai/free/en/universities/tel-aviv-university/) — University, Tel Aviv, Israel · 82 works · 10,655 citations
- [Centre National de la Recherche Scientifique](https://md.research.elamur.ai/free/en/labs/centre-national-de-la-recherche-scientifique/) — Research institute, Paris, France · 168 works · 62,369 citations
- [École Normale Supérieure - PSL](https://md.research.elamur.ai/free/en/labs/ecole-normale-superieure-psl/) — Research institute, Paris, France · 23 works · 4,357 citations
- [Université Paris Sciences et Lettres](https://md.research.elamur.ai/free/en/universities/universite-paris-sciences-et-lettres/) — University, Paris, France · 21 works · 3,290 citations
- [École des hautes études en sciences sociales](https://md.research.elamur.ai/free/en/labs/ecole-des-hautes-etudes-en-sciences-sociales/) — Research institute, Paris, France · 15 works · 2,302 citations
- [Laboratoire de Sciences Cognitives et Psycholinguistique](https://md.research.elamur.ai/free/en/labs/laboratoire-de-sciences-cognitives-et-psycholinguistique/) — Research institute, Paris, France · 7 works · 907 citations

📚 Shelves (4): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 16,667 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 16,194 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 16,039 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 15,891 works

🧭 Topics (1): [🧠 Language models & pretraining](https://md.research.elamur.ai/free/en/topics/language-models/) · 3,320 works

## Cite

Cite as: Imry Ziv, Nur Lan and Emmanuel Chemla. 2026. Biasless Language Models Learn Unnaturally: How LLMs Fail to Distinguish the Possible from the Impossible. Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers).

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

```bibtex
@inproceedings{ziv2026biasless,
  title = {{Biasless Language Models Learn Unnaturally: How LLMs Fail to Distinguish the Possible from the Impossible}},
  author = {Imry Ziv, Nur Lan and Emmanuel Chemla},
  booktitle = {Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)},
  year = {2026},
  doi = {10.18653/v1/2026.eacl-long.249},
  url = {https://doi.org/10.18653/v1/2026.eacl-long.249}
}
```

- [← previous Beyond “I Don't Know”: Evaluating LLM Self-Awareness in Discriminating Data and Model Uncertainty](https://md.research.elamur.ai/free/en/papers/ren-2026-beyond-i-don-t-know/)
- [next → Bit-by-Bit: Progressive QAT Strategy with Outlier Channel Splitting for Stable Low-Bit LLMs](https://md.research.elamur.ai/free/en/papers/xu-2026-bit-bit-progressive-qat-strategy/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/5/)

## References

48 references, 10 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Mostafa Abdou, Vinit Ravishankar, Artur Kulmizev, and Anders Søgaard. 2022. Word order does matter and shuffled language models know it. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 6907–6919, Dublin, Ireland. Association f… [find](https://scholar.google.com/scholar?q=Mostafa+Abdou%2C+Vinit+Ravishankar%2C+Artur+Kulmizev%2C+and+Anders+S%C3%B8gaard%2E+2022%2E+Word+order+does+matter+and+shuffled+language+models+know+it%2E+In+Proceedings+of+the+60th+Annual+Meeting+of+the+Association+fo)
2. Catherine Arnett and Benjamin K. Bergen. 2025. [Why do language models perform worse for morphologically complex languages?](https://md.research.elamur.ai/free/en/papers/arnett-2025-why-do-language-models-perform/) In Proceedings of the 31st International Conference on Computational Linguistics (COLING 2025), pages 6607– 6622, Mexico City, Mexico. Association for Computational Linguistics.
3. Mark Baker. 2012. Formal generative typology. [find](https://scholar.google.com/scholar?q=Mark+Baker%2E+2012%2E+Formal+generative+typology%2E)
4. Marco Baroni. 2022. On the proper role of linguistically-oriented deep net analysis in linguistic theorizing. In Shalom Lappin and Jürgen Bernardy, editors, Algebraic Structures in Natural Language, pages 1–16. CRC Press / Taylor Francis. Preprint available as arXiv:2106.08694. — [arXiv:2106.08694](https://arxiv.org/abs/2106.08694) [find](https://scholar.google.com/scholar?q=Marco+Baroni%2E+2022%2E+On+the+proper+role+of+linguistically%2Doriented+deep+net+analysis+in+linguistic+theorizing%2E+In+Shalom+Lappin+and+J%C3%BCrgen+Bernardy%2C+editors%2C+Algebraic+Structures+in+Natural+Language%2C+p)
5. Thomas Brochhagen, Michael Franke, and Robert van Rooij. 2018. Coevolution of lexical meaning and pragmatic use. Cognitive Science, 42(8):2757– 2789. [find](https://scholar.google.com/scholar?q=Thomas+Brochhagen%2C+Michael+Franke%2C+and+Robert+van+Rooij%2E+2018%2E+Coevolution+of+lexical+meaning+and+pragmatic+use%2E+Cognitive+Science%2C+42%288%29%3A2757%E2%80%93+2789%2E)
6. Emmanuel Chemla and Ryan Nefdt. 2024. No such thing as a general learner: Language models and their dual optimization. Ms. [find](https://scholar.google.com/scholar?q=Emmanuel+Chemla+and+Ryan+Nefdt%2E+2024%2E+No+such+thing+as+a+general+learner%3A+Language+models+and+their+dual+optimization%2E+Ms%2E)
7. Noam Chomsky. 1957. Syntactic Structures. Mouton, The Hague. [find](https://scholar.google.com/scholar?q=Noam+Chomsky%2E+1957%2E+Syntactic+Structures%2E+Mouton%2C+The+Hague%2E)
8. Noam Chomsky. 1965. Aspects of the Theory of Syntax. MIT Press, Cambridge, MA. [find](https://scholar.google.com/scholar?q=Noam+Chomsky%2E+1965%2E+Aspects+of+the+Theory+of+Syntax%2E+MIT+Press%2C+Cambridge%2C+MA%2E)
9. Noam Chomsky. 1981. Lectures on Government and Binding. Foris Publications, Dordrecht, Netherlands. [find](https://scholar.google.com/scholar?q=Noam+Chomsky%2E+1981%2E+Lectures+on+Government+and+Binding%2E+Foris+Publications%2C+Dordrecht%2C+Netherlands%2E)
10. Noam Chomsky. 2000. New Horizons in the Study of Language and Mind. Cambridge University Press, Cambridge; New York. Hardback edition, with foreword by Neil Smith. [find](https://scholar.google.com/scholar?q=Noam+Chomsky%2E+2000%2E+New+Horizons+in+the+Study+of+Language+and+Mind%2E+Cambridge+University+Press%2C+Cambridge%3B+New+York%2E+Hardback+edition%2C+with+foreword+by+Neil+Smith%2E)
11. Noam Chomsky, Ian Roberts, and Jeffrey Watumull. 2023. Noam chomsky: The false promise of chatgpt. The New York Times. Accessed: 2025-09-10. [find](https://scholar.google.com/scholar?q=Noam+Chomsky%2C+Ian+Roberts%2C+and+Jeffrey+Watumull%2E+2023%2E+Noam+chomsky%3A+The+false+promise+of+chatgpt%2E+The+New+York+Times%2E+Accessed%3A+2025%2D09%2D10%2E)
12. Thomas Hikaru Clark, Clara Meister, Tiago Pimentel, Michael Hahn, Ryan Cotterell, Richard Futrell, and Roger Levy. 2023. [A cross-linguistic pressure for uniform information density in word order](https://md.research.elamur.ai/free/en/papers/clark-2023-cross-linguistic-pressure-uniform-information/). Transactions of the Association for Computational Linguistics, 11:1048–1065.
13. Jeremy Collins. 2016. Some language universals are historical accidents. In Karsten Schmidtke-Bode, Natalia Levshina, Susanne Maria Michaelis, and Ilja A. Serant, editors, Explanation in Typology: Diachronic Sources, Functional Motivations and the Nature of the Evidence, pages 51–65. Language Scienc… [find](https://scholar.google.com/scholar?q=Jeremy+Collins%2E+2016%2E+Some+language+universals+are+historical+accidents%2E+In+Karsten+Schmidtke%2DBode%2C+Natalia+Levshina%2C+Susanne+Maria+Michaelis%2C+and+Ilja+A%2E+Serant%2C+editors%2C+Explanation+in+Typology%3A+Dia)
14. Jennifer Culbertson and Elissa L. Newport. 2015. Harmonic biases in child learners: In support of language universals. Cognition, 139:71–82. [find](https://scholar.google.com/scholar?q=Jennifer+Culbertson+and+Elissa+L%2E+Newport%2E+2015%2E+Harmonic+biases+in+child+learners%3A+In+support+of+language+universals%2E+Cognition%2C+139%3A71%E2%80%9382%2E)
15. Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2018. [BERT: pre-training of deep bidirectional transformers for language understanding](https://md.research.elamur.ai/free/en/papers/devlin-2019-bert-pre-training-deep-bidirectional/). CoRR, abs/1810.04805.
16. Jeffrey L. Elman. 1990. Finding structure in time. Cognitive Science, 14(2):179–211. [find](https://scholar.google.com/scholar?q=Jeffrey+L%2E+Elman%2E+1990%2E+Finding+structure+in+time%2E+Cognitive+Science%2C+14%282%29%3A179%E2%80%93211%2E)
17. Sandiway Fong and Robert C. Berwick. 2008. Treebank parsing and knowledge of language: A cognitive perspective. In Proceedings of the 30th Annual Conference of the Cognitive Science Society, page 539, Washington, DC. Cognitive Science Society. Paper No. 539. [find](https://scholar.google.com/scholar?q=Sandiway+Fong+and+Robert+C%2E+Berwick%2E+2008%2E+Treebank+parsing+and+knowledge+of+language%3A+A+cognitive+perspective%2E+In+Proceedings+of+the+30th+Annual+Conference+of+the+Cognitive+Science+Society%2C+page+539%2C)
18. Sandiway Fong, Igor Malioutov, Beracah Yankama, and Robert C. Berwick. 2013. Treebank parsing and knowledge of language. In Aline Villavicencio, Thierry Poibeau, Anna Korhonen, and Afra Alishahi, editors, Cognitive Aspects of Computational Language Acquisition, Theory and Applications of Natural Lan… [find](https://scholar.google.com/scholar?q=Sandiway+Fong%2C+Igor+Malioutov%2C+Beracah+Yankama%2C+and+Robert+C%2E+Berwick%2E+2013%2E+Treebank+parsing+and+knowledge+of+language%2E+In+Aline+Villavicencio%2C+Thierry+Poibeau%2C+Anna+Korhonen%2C+and+Afra+Alishahi%2C+edit)
19. Danny Fox and Roni Katzir. 2024. Large language models and theoretical linguistics. Theoretical Linguistics, 50(1–2):71–76. [find](https://scholar.google.com/scholar?q=Danny+Fox+and+Roni+Katzir%2E+2024%2E+Large+language+models+and+theoretical+linguistics%2E+Theoretical+Linguistics%2C+50%281%E2%80%932%29%3A71%E2%80%9376%2E)
20. Richard Futrell and Michael Hahn. 2022. Information theory as a bridge between language function and language form. Frontiers in Communication, 7(657725). [find](https://scholar.google.com/scholar?q=Richard+Futrell+and+Michael+Hahn%2E+2022%2E+Information+theory+as+a+bridge+between+language+function+and+language+form%2E+Frontiers+in+Communication%2C+7%28657725%29%2E)
21. Richard Futrell and Michael Hahn. 2025. Linguistic structure from a bottleneck on sequential information processing. Nature Human Behaviour. [find](https://scholar.google.com/scholar?q=Richard+Futrell+and+Michael+Hahn%2E+2025%2E+Linguistic+structure+from+a+bottleneck+on+sequential+information+processing%2E+Nature+Human+Behaviour%2E)
22. Richard Futrell and Kyle Mahowald. 2025. How linguistics learned to stop worrying and love the language models. Behavioral and Brain Sciences. Accepted manuscript. [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%2E+Accepted+manuscript%2E)
23. Kristina Gulordava, Piotr Bojanowski, Edouard Grave, Tal Linzen, and Marco Baroni. 2018. [Colorless green recurrent networks dream hierarchically](https://md.research.elamur.ai/free/en/papers/gulordava-2018-colorless-green-recurrent-networks-dream/). In Proceedings of NAACL 2018, pages 1195–1205.
24. Marc D. Hauser, Noam Chomsky, and W. Tecumseh Fitch. 2002. The faculty of language: What is it, who has it, and how did it evolve? Science, 298(5598):1569–1579. [find](https://scholar.google.com/scholar?q=Marc+D%2E+Hauser%2C+Noam+Chomsky%2C+and+W%2E+Tecumseh+Fitch%2E+2002%2E+The+faculty+of+language%3A+What+is+it%2C+who+has+it%2C+and+how+did+it+evolve%3F+Science%2C+298%285598%29%3A1569%E2%80%931579%2E)
25. Tim Hunter. 2025. Kallini et al. (2024) do not compare impossible languages with constituency-based ones. Computational Linguistics, 51(2):641–650. [find](https://scholar.google.com/scholar?q=Tim+Hunter%2E+2025%2E+Kallini+et+al%2E+%282024%29+do+not+compare+impossible+languages+with+constituency%2Dbased+ones%2E+Computational+Linguistics%2C+51%282%29%3A641%E2%80%93650%2E)
26. Julie Kallini, Isabel Papadimitriou, Richard Futrell, Kyle Mahowald, and Christopher Potts. 2024. [Mission: Impossible language models](https://md.research.elamur.ai/free/en/papers/kallini-2024-mission-impossible-language-models/). In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 14691–14714, Bangkok, Thailand. Association…
27. Simon Kirby, Mike Dowman, and Thomas L. Griffiths. 2007. Innateness and culture in the evolution of language. Proceedings of the National Academy of Sciences, 104(12):5241–5245. [find](https://scholar.google.com/scholar?q=Simon+Kirby%2C+Mike+Dowman%2C+and+Thomas+L%2E+Griffiths%2E+2007%2E+Innateness+and+culture+in+the+evolution+of+language%2E+Proceedings+of+the+National+Academy+of+Sciences%2C+104%2812%29%3A5241%E2%80%935245%2E)
28. Nur Lan, Emmanuel Chemla, and Roni Katzir. 2024. Large language models and the argument from the poverty of the stimulus. Linguistic Inquiry, pages 1–56. [find](https://scholar.google.com/scholar?q=Nur+Lan%2C+Emmanuel+Chemla%2C+and+Roni+Katzir%2E+2024%2E+Large+language+models+and+the+argument+from+the+poverty+of+the+stimulus%2E+Linguistic+Inquiry%2C+pages+1%E2%80%9356%2E)
29. Evelina Leivada, Raquel Montero, Paolo Morosi, Natalia Moskvina, Tamara Serrano, Marcel Aguilar, and Fritz Guenther. 2025. Large language model probabilities cannot distinguish between possible and impossible language. arXiv preprint, arXiv:2509.15114. Submitted on 18 Sep 2025. — [arXiv:2509.15114](https://arxiv.org/abs/2509.15114) [find](https://scholar.google.com/scholar?q=Evelina+Leivada%2C+Raquel+Montero%2C+Paolo+Morosi%2C+Natalia+Moskvina%2C+Tamara+Serrano%2C+Marcel+Aguilar%2C+and+Fritz+Guenther%2E+2025%2E+Large+language+model+probabilities+cannot+distinguish+between+possible+and+im)
30. Tal Linzen and Marco Baroni. 2020. Syntactic structure from deep learning. Annual Reviews of Linguistics. [find](https://scholar.google.com/scholar?q=Tal+Linzen+and+Marco+Baroni%2E+2020%2E+Syntactic+structure+from+deep+learning%2E+Annual+Reviews+of+Linguistics%2E)
31. Kyle Mahowald, Anna A. Ivanova, Idan A. Blank, Nancy Kanwisher, Joshua B. Tenenbaum, and Evelina Fedorenko. 2024. Dissociating language and thought in large language models. Trends in Cognitive Sciences, 28(6):517–540. [find](https://scholar.google.com/scholar?q=Kyle+Mahowald%2C+Anna+A%2E+Ivanova%2C+Idan+A%2E+Blank%2C+Nancy+Kanwisher%2C+Joshua+B%2E+Tenenbaum%2C+and+Evelina+Fedorenko%2E+2024%2E+Dissociating+language+and+thought+in+large+language+models%2E+Trends+in+Cognitive+Scienc)
32. Daniel Milway. 2025. On modern language models, impossible languages and anti-science. Ling-Buzz preprint. [https://ling.auf.net/lingbuzz/](https://ling.auf.net/lingbuzz/) 008314. [↗](https://ling.auf.net/lingbuzz/)
33. Jeff Mitchell and Jeffrey Bowers. 2020. Priorless recurrent networks learn curiously. In Proceedings of the 28th International Conference on Computational Linguistics. [find](https://scholar.google.com/scholar?q=Jeff+Mitchell+and+Jeffrey+Bowers%2E+2020%2E+Priorless+recurrent+networks+learn+curiously%2E+In+Proceedings+of+the+28th+International+Conference+on+Computational+Linguistics%2E)
34. Andrea Moro. 2016. Impossible Languages. Press, Cambridge, MA. [find](https://scholar.google.com/scholar?q=Andrea+Moro%2E+2016%2E+Impossible+Languages%2E+Press%2C+Cambridge%2C+MA%2E)
35. MIT Andrea Moro, Matteo Greco, and Stefano F. Cappa. 2023. Large languages, impossible languages and human brains. Cortex, 167:82–85. [find](https://scholar.google.com/scholar?q=MIT+Andrea+Moro%2C+Matteo+Greco%2C+and+Stefano+F%2E+Cappa%2E+2023%2E+Large+languages%2C+impossible+languages+and+human+brains%2E+Cortex%2C+167%3A82%E2%80%9385%2E)
36. Mariacristina Musso, Andrea Moro, Volkmar Glauche, Michel Rijntjes, Juergen Reichenbach, Christian Büchel, and Cornelius Weiller. 2003. Broca’s area and the language instinct. Nature Neuroscience, 6(7):774–781. [find](https://scholar.google.com/scholar?q=Mariacristina+Musso%2C+Andrea+Moro%2C+Volkmar+Glauche%2C+Michel+Rijntjes%2C+Juergen+Reichenbach%2C+Christian+B%C3%BCchel%2C+and+Cornelius+Weiller%2E+2003%2E+Broca%E2%80%99s+area+and+the+language+instinct%2E+Nature+Neuroscience%2C+6%287)
37. Partha Niyogi and Robert C. Berwick. 2009. The proper treatment of language acquisition and change in a population setting. Proceedings of the National Academy of Sciences, 106:10124–10129. [find](https://scholar.google.com/scholar?q=Partha+Niyogi+and+Robert+C%2E+Berwick%2E+2009%2E+The+proper+treatment+of+language+acquisition+and+change+in+a+population+setting%2E+Proceedings+of+the+National+Academy+of+Sciences%2C+106%3A10124%E2%80%9310129%2E)
38. Alec Radford, Jeffrey Wu, Rewon Child, David Luan, Dario Amodei, and Ilya Sutskever. 2019. Language models are unsupervised multitask learners. OpenAI. Accessed: 2024-11-15. [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+OpenAI%2E+Accessed%3A+2024%2D11%2D15%2E)
39. John R. Ross. 1967. Constraints on Variables in Syntax. Ph.D. thesis, MIT, Cambridge, MA. [find](https://scholar.google.com/scholar?q=John+R%2E+Ross%2E+1967%2E+Constraints+on+Variables+in+Syntax%2E+Ph%2ED%2E+thesis%2C+MIT%2C+Cambridge%2C+MA%2E)
40. H. Schmid. 1999. Improvements in Part-of-Speech Tagging with an Application to German, pages 13–25. Springer Netherlands, Dordrecht. [find](https://scholar.google.com/scholar?q=H%2E+Schmid%2E+1999%2E+Improvements+in+Part%2Dof%2DSpeech+Tagging+with+an+Application+to+German%2C+pages+13%E2%80%9325%2E+Springer+Netherlands%2C+Dordrecht%2E)
41. Avi Shmidman and Shaltiel Shmidman. 2025. [Restoring missing spaces in scraped Hebrew social media](https://md.research.elamur.ai/free/en/papers/shmidman-2025-restoring-missing-spaces-scraped-hebrew/). In Proceedings of the Tenth Workshop on Noisy and User-generated Text, pages 16–25, Albuquerque, New Mexico, USA. Association for Computational Linguistics.
42. Koustuv Sinha, Robin Jia, Dieuwke Hupkes, Joelle Pineau, Adina Williams, and Douwe Kiela. 2021. [Masked language modeling and the distributional hypothesis: Order word matters pre-training for little](https://md.research.elamur.ai/free/en/papers/sinha-2021-masked-language-modeling-distributional-hypothesis/). In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 288…
43. Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Łukasz Kaiser, and Illia Polosukhin. 2017. [Attention is all you need](https://md.research.elamur.ai/free/en/papers/vaswani-2017-attention-all-need/). In Advances in Neural Information Processing Systems (NeurIPS 2017), volume 30, pages 5998–6008. Curran Associates, Inc.
44. Ethan Gotlieb Wilcox, Richard Futrell, and Roger Levy. 2023. Using computational models to test syntactic learnability. Linguistic Inquiry, pages 1–44. [find](https://scholar.google.com/scholar?q=Ethan+Gotlieb+Wilcox%2C+Richard+Futrell%2C+and+Roger+Levy%2E+2023%2E+Using+computational+models+to+test+syntactic+learnability%2E+Linguistic+Inquiry%2C+pages+1%E2%80%9344%2E)
45. Tianyang Xu, Tatsuki Kuribayashi, Yohei Oseki, Ryan Cotterell, and Alex Warstadt. 2025. [Can language models learn typologically implausible languages?](https://md.research.elamur.ai/free/en/papers/xu-2026-can-language-models-learn-typologically/) Preprint, arXiv:2502.12317.
46. Xiulin Yang, Tatsuya Aoyama, Yuekun Yao, and Ethan Wilcox. 2025. [Anything goes? a crosslinguistic study of (im)possible language learning in LMs](https://md.research.elamur.ai/free/en/papers/yang-2025-anything-goes-crosslinguistic-study-im/). In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 26058–26077, Vienna, Austria. As…
47. Victor H. Yngve. 1960. A model and an hypothesis for language structure. Proceedings of the American Philosophical Society, 104(5):444–466. [find](https://scholar.google.com/scholar?q=Victor+H%2E+Yngve%2E+1960%2E+A+model+and+an+hypothesis+for+language+structure%2E+Proceedings+of+the+American+Philosophical+Society%2C+104%285%29%3A444%E2%80%93466%2E)
48. Imry Ziv, Nur Lan, Emmanuel Chemla, and Roni Katzir. 2025. Large Language Models as Proxies for Theories of Human Linguistic Cognition. Preprint, arXiv:2502.07687. [find](https://scholar.google.com/scholar?q=Imry+Ziv%2C+Nur+Lan%2C+Emmanuel+Chemla%2C+and+Roni+Katzir%2E+2025%2E+Large+Language+Models+as+Proxies+for+Theories+of+Human+Linguistic+Cognition%2E+Preprint%2C+arXiv%3A2502%2E07687%2E)

*Updated 31 October 2026*