Menu
Home Explore People Places Arts History Plants & Animals Science Life & Culture Technology
On this page
Stochastic parrot
Term used in machine learning

In machine learning, the term stochastic parrot, coined by Emily M. Bender and colleagues in 2021, criticizes large language models (LLMs) as systems that statistically mimic text without true understanding. Their paper argues LLMs probabilistically link words without meaning, emphasizing two limitations: LLMs are bound by their training data and cannot discern correctness or appropriateness of outputs. However, this metaphor faces criticism for employing a straw man fallacy by oversimplifying language-model research and a false dichotomy that ignores emerging reasoning abilities documented by experts like Geoffrey Hinton. While poor data quality can cause "dangerously wrong" outcomes, ongoing studies reveal that modern LLMs exhibit problem-solving skills beyond mere parroting.

We don't have any images related to Stochastic parrot yet.
We don't have any YouTube videos related to Stochastic parrot yet.
We don't have any PDF documents related to Stochastic parrot yet.
We don't have any Books related to Stochastic parrot yet.

Subsequent usage

Stochastic parrot is now a neologism used by AI skeptics to allege that LLM's lack understanding of the meaning of their outputs and is sometimes interpreted as a "slur against AI".10 Its use expanded further when Sam Altman, CEO of Open AI, used the term ironically when he tweeted, "i am a stochastic parrot and so r u", pointing out that, by the same reasoning, one could also disparage humans as mere next-word predictors whose brains (or pens) simply generate statistically likely sequences.11 The term was then designated to be the 2023 AI-related Word of the Year for the American Dialect Society, even over the words "ChatGPT" and "LLM".1213

The phrase is often referenced by some researchers to describe LLMs as pattern matchers that can generate plausible human-like text through their vast amount of training data, merely parroting in a stochastic fashion. However, other researchers argue that LLMs are, in fact, at least partially able to understand language.14

Debate

Some LLMs, such as ChatGPT, have become capable of interacting with users in convincingly human-like conversations.15 The development of these new systems has deepened the discussion of the extent to which LLMs understand or are simply "parroting".

Subjective experience

In the mind of a human being, words and language correspond to things one has experienced.16 For LLMs, words may correspond only to other words and patterns of usage fed into their training data.171819 Proponents of the idea of stochastic parrots thus conclude that LLMs are incapable of actually understanding language.2021

Hallucinations and mistakes

The tendency of LLMs to pass off fake information as fact is held as support.22 Called hallucinations or confabulations, LLMs will occasionally synthesize information that matches some pattern, but not reality.232425 That LLMs can’t distinguish fact and fiction leads to the claim that they can’t connect words to a comprehension of the world, as language should do.2627 Further, LLMs often fail to decipher complex or ambiguous grammar cases that rely on understanding the meaning of language.2829 As an example, borrowing from Saba et al., is the prompt:30

The wet newspaper that fell down off the table is my favorite newspaper. But now that my favorite newspaper fired the editor I might not like reading it anymore. Can I replace ‘my favorite newspaper’ by ‘the wet newspaper that fell down off the table’ in the second sentence?

Some LLMs respond to this in the affirmative, not understanding that the meaning of "newspaper" is different in these two contexts; it is first an object and second an institution.31 Based on these failures, some AI professionals conclude they are no more than stochastic parrots.323334

Benchmarks and experiments

One argument against the hypothesis that LLMs are stochastic parrot is their results on benchmarks for reasoning, common sense and language understanding. In 2023, some LLMs have shown good results on many language understanding tests, such as the Super General Language Understanding Evaluation (SuperGLUE).3536 GPT-4 scored in the >90th-percentile on the Uniform Bar Examination and achieved 93% accuracy on the MATH benchmark of high-school Olympiad problems, results that exceed rote pattern-matching expectations.37 Such tests, and the smoothness of many LLM responses, help as many as 51% of AI professionals believe they can truly understand language with enough data, according to a 2022 survey.38

Expert rebuttals

Leading AI researchers dispute the notion that LLMs merely “parrot” their training data.

  • Geoffrey Hinton argues that “to predict the next word accurately you have to understand the sentence”, a view he presented on 60 Minutes in 2023.39 He also uses logical puzzles to demonstrate that LLMs actually understand language.40
  • A 2024 Scientific American investigation described a closed Berkeley workshop where state-of-the-art models solved novel tier-4 mathematics problems and produced coherent proofs, indicating reasoning abilities beyond memorization.41
  • The GPT-4 Technical Report showed human-level results on professional and academic exams (e.g., the Uniform Bar Exam and USMLE), challenging the “parrot” characterization.42

Interpretability

Another technique for investigating if LLMs can understand is termed "mechanistic interpretability". The idea is to reverse-engineer a large language model to analyze how it internally processes the information.

One example is Othello-GPT, where a small transformer was trained to predict legal Othello moves. It has been found that this model has an internal representation of the Othello board, and that modifying this representation changes the predicted legal Othello moves in the correct way. This supports the idea that LLMs have a "world model", and are not just doing superficial statistics.4344

In another example, a small transformer was trained on computer programs written in the programming language Karel. Similar to the Othello-GPT example, this model developed an internal representation of Karel program semantics. Modifying this representation results in appropriate changes to the output. Additionally, the model generates correct programs that are, on average, shorter than those in the training set.45

Researchers also studied "grokking", a phenomenon where an AI model initially memorizes the training data outputs, and then, after further training, suddenly finds a solution that generalizes to unseen data.46

Shortcuts to reasoning

However, when tests created to test people for language comprehension are used to test LLMs, they sometimes result in false positives caused by spurious correlations within text data.47 Models have shown examples of shortcut learning, which is when a system makes unrelated correlations within data instead of using human-like understanding.48 One such experiment conducted in 2019 tested Google’s BERT LLM using the argument reasoning comprehension task. BERT was prompted to choose between 2 statements, and find the one most consistent with an argument. Below is an example of one of these prompts:4950

Argument: Felons should be allowed to vote. A person who stole a car at 17 should not be barred from being a full citizen for life. Statement A: Grand theft auto is a felony. Statement B: Grand theft auto is not a felony.

Researchers found that specific words such as "not" hint the model towards the correct answer, allowing near-perfect scores when included but resulting in random selection when hint words were removed.5152 This problem, and the known difficulties defining intelligence, causes some to argue all benchmarks that find understanding in LLMs are flawed, that they all allow shortcuts to fake understanding.

See also

Works cited

Further reading

References

  1. Bender, Emily M.; Gebru, Timnit; McMillan-Major, Angelina; Mitchell, Margaret (2021). "On the Dangers of Stochastic Parrots: Can Language Models Be Too Big?". Proceedings of the 2021 ACM Conference on Fairness, Accountability, and Transparency. doi:10.1145/3442188.3445922. /wiki/Doi_(identifier) ↩

  2. Bubeck, Sébastien (2023). "Sparks of Artificial General Intelligence: Early experiments with GPT-4". arXiv:2303.12712. A bot will complete this citation soon. Click here to jump the queue /wiki/ArXiv_(identifier) ↩

  3. Pelley, Scott (8 October 2023). ""Godfather of Artificial Intelligence" Geoffrey Hinton on the promise, risks of advanced AI". CBS News. Retrieved 2 July 2025. https://www.cbsnews.com/news/geoffrey-hinton-ai-dangers-60-minutes-transcript/ ↩

  4. Bender, Emily M.; Gebru, Timnit; McMillan-Major, Angelina; Mitchell, Margaret (2021). "On the Dangers of Stochastic Parrots: Can Language Models Be Too Big?". Proceedings of the 2021 ACM Conference on Fairness, Accountability, and Transparency. doi:10.1145/3442188.3445922. /wiki/Doi_(identifier) ↩

  5. Lindholm et al. 2022, pp. 322–3. - Lindholm, A.; Wahlström, N.; Lindsten, F.; Schön, T. B. (2022). Machine Learning: A First Course for Engineers and Scientists. Cambridge University Press. ISBN 978-1108843607. ↩

  6. Uddin, Muhammad Saad (April 20, 2023). "Stochastic Parrots: A Novel Look at Large Language Models and Their Limitations". Towards AI. Retrieved 2023-05-12. https://towardsai.net/p/machine-learning/stochastic-parrots-a-novel-look-at-large-language-models-and-their-limitations ↩

  7. Pelley, Scott (8 October 2023). ""Godfather of Artificial Intelligence" Geoffrey Hinton on the promise, risks of advanced AI". CBS News. Retrieved 2 July 2025. https://www.cbsnews.com/news/geoffrey-hinton-ai-dangers-60-minutes-transcript/ ↩

  8. Bubeck, Sébastien (2023). "Sparks of Artificial General Intelligence: Early experiments with GPT-4". arXiv:2303.12712. A bot will complete this citation soon. Click here to jump the queue /wiki/ArXiv_(identifier) ↩

  9. Lindholm et al. 2022, pp. 322–3. - Lindholm, A.; Wahlström, N.; Lindsten, F.; Schön, T. B. (2022). Machine Learning: A First Course for Engineers and Scientists. Cambridge University Press. ISBN 978-1108843607. ↩

  10. Zimmer, Ben (2024-01-18). "'Stochastic Parrot': A Name for AI That Sounds a Bit Less Intelligent". Wall Street Journal. Retrieved 2024-04-01. https://www.wsj.com/arts-culture/books/stochastic-parrot-a-name-for-ai-that-sounds-a-bit-less-intelligent-789372f5 ↩

  11. Zimmer, Ben (2024-01-18). "'Stochastic Parrot': A Name for AI That Sounds a Bit Less Intelligent". Wall Street Journal. Retrieved 2024-04-01. https://www.wsj.com/arts-culture/books/stochastic-parrot-a-name-for-ai-that-sounds-a-bit-less-intelligent-789372f5 ↩

  12. Zimmer, Ben (2024-01-18). "'Stochastic Parrot': A Name for AI That Sounds a Bit Less Intelligent". Wall Street Journal. Retrieved 2024-04-01. https://www.wsj.com/arts-culture/books/stochastic-parrot-a-name-for-ai-that-sounds-a-bit-less-intelligent-789372f5 ↩

  13. Corbin, Sam (2024-01-15). "Among Linguists, the Word of the Year Is More of a Vibe". The New York Times. ISSN 0362-4331. Retrieved 2024-04-01. https://www.nytimes.com/2024/01/15/crosswords/linguistics-word-of-the-year.html ↩

  14. Arkoudas, Konstantine (2023-08-21). "ChatGPT is no Stochastic Parrot. But it also Claims that 1 is Greater than 1". Philosophy & Technology. 36 (3): 54. doi:10.1007/s13347-023-00619-6. ISSN 2210-5441. https://doi.org/10.1007/s13347-023-00619-6 ↩

  15. Arkoudas, Konstantine (2023-08-21). "ChatGPT is no Stochastic Parrot. But it also Claims that 1 is Greater than 1". Philosophy & Technology. 36 (3): 54. doi:10.1007/s13347-023-00619-6. ISSN 2210-5441. https://doi.org/10.1007/s13347-023-00619-6 ↩

  16. Fayyad, Usama M. (2023-05-26). "From Stochastic Parrots to Intelligent Assistants—The Secrets of Data and Human Interventions". IEEE Intelligent Systems. 38 (3): 63–67. doi:10.1109/MIS.2023.3268723. ISSN 1541-1672. https://ieeexplore.ieee.org/document/10148666 ↩

  17. Saba, Walid S. (2023). "Stochastic LLMS do not Understand Language: Towards Symbolic, Explainable and Ontologically Based LLMS". In Almeida, João Paulo A.; Borbinha, José; Guizzardi, Giancarlo; Link, Sebastian; Zdravkovic, Jelena (eds.). Conceptual Modeling. Lecture Notes in Computer Science. Vol. 14320. Cham: Springer Nature Switzerland. pp. 3–19. arXiv:2309.05918. doi:10.1007/978-3-031-47262-6_1. ISBN 978-3-031-47262-6. 978-3-031-47262-6 ↩

  18. Mitchell, Melanie; Krakauer, David C. (2023-03-28). "The debate over understanding in AI's large language models". Proceedings of the National Academy of Sciences. 120 (13): e2215907120. arXiv:2210.13966. Bibcode:2023PNAS..12015907M. doi:10.1073/pnas.2215907120. ISSN 0027-8424. PMC 10068812. PMID 36943882. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10068812 ↩

  19. Bender, Emily M.; Gebru, Timnit; McMillan-Major, Angelina; Mitchell, Margaret (2021). "On the Dangers of Stochastic Parrots: Can Language Models Be Too Big?". Proceedings of the 2021 ACM Conference on Fairness, Accountability, and Transparency. doi:10.1145/3442188.3445922. /wiki/Doi_(identifier) ↩

  20. Saba, Walid S. (2023). "Stochastic LLMS do not Understand Language: Towards Symbolic, Explainable and Ontologically Based LLMS". In Almeida, João Paulo A.; Borbinha, José; Guizzardi, Giancarlo; Link, Sebastian; Zdravkovic, Jelena (eds.). Conceptual Modeling. Lecture Notes in Computer Science. Vol. 14320. Cham: Springer Nature Switzerland. pp. 3–19. arXiv:2309.05918. doi:10.1007/978-3-031-47262-6_1. ISBN 978-3-031-47262-6. 978-3-031-47262-6 ↩

  21. Bender, Emily M.; Gebru, Timnit; McMillan-Major, Angelina; Mitchell, Margaret (2021). "On the Dangers of Stochastic Parrots: Can Language Models Be Too Big?". Proceedings of the 2021 ACM Conference on Fairness, Accountability, and Transparency. doi:10.1145/3442188.3445922. /wiki/Doi_(identifier) ↩

  22. Fayyad, Usama M. (2023-05-26). "From Stochastic Parrots to Intelligent Assistants—The Secrets of Data and Human Interventions". IEEE Intelligent Systems. 38 (3): 63–67. doi:10.1109/MIS.2023.3268723. ISSN 1541-1672. https://ieeexplore.ieee.org/document/10148666 ↩

  23. Saba, Walid S. (2023). "Stochastic LLMS do not Understand Language: Towards Symbolic, Explainable and Ontologically Based LLMS". In Almeida, João Paulo A.; Borbinha, José; Guizzardi, Giancarlo; Link, Sebastian; Zdravkovic, Jelena (eds.). Conceptual Modeling. Lecture Notes in Computer Science. Vol. 14320. Cham: Springer Nature Switzerland. pp. 3–19. arXiv:2309.05918. doi:10.1007/978-3-031-47262-6_1. ISBN 978-3-031-47262-6. 978-3-031-47262-6 ↩

  24. Mitchell, Melanie; Krakauer, David C. (2023-03-28). "The debate over understanding in AI's large language models". Proceedings of the National Academy of Sciences. 120 (13): e2215907120. arXiv:2210.13966. Bibcode:2023PNAS..12015907M. doi:10.1073/pnas.2215907120. ISSN 0027-8424. PMC 10068812. PMID 36943882. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10068812 ↩

  25. Fayyad, Usama M. (2023-05-26). "From Stochastic Parrots to Intelligent Assistants—The Secrets of Data and Human Interventions". IEEE Intelligent Systems. 38 (3): 63–67. doi:10.1109/MIS.2023.3268723. ISSN 1541-1672. https://ieeexplore.ieee.org/document/10148666 ↩

  26. Saba, Walid S. (2023). "Stochastic LLMS do not Understand Language: Towards Symbolic, Explainable and Ontologically Based LLMS". In Almeida, João Paulo A.; Borbinha, José; Guizzardi, Giancarlo; Link, Sebastian; Zdravkovic, Jelena (eds.). Conceptual Modeling. Lecture Notes in Computer Science. Vol. 14320. Cham: Springer Nature Switzerland. pp. 3–19. arXiv:2309.05918. doi:10.1007/978-3-031-47262-6_1. ISBN 978-3-031-47262-6. 978-3-031-47262-6 ↩

  27. Fayyad, Usama M. (2023-05-26). "From Stochastic Parrots to Intelligent Assistants—The Secrets of Data and Human Interventions". IEEE Intelligent Systems. 38 (3): 63–67. doi:10.1109/MIS.2023.3268723. ISSN 1541-1672. https://ieeexplore.ieee.org/document/10148666 ↩

  28. Saba, Walid S. (2023). "Stochastic LLMS do not Understand Language: Towards Symbolic, Explainable and Ontologically Based LLMS". In Almeida, João Paulo A.; Borbinha, José; Guizzardi, Giancarlo; Link, Sebastian; Zdravkovic, Jelena (eds.). Conceptual Modeling. Lecture Notes in Computer Science. Vol. 14320. Cham: Springer Nature Switzerland. pp. 3–19. arXiv:2309.05918. doi:10.1007/978-3-031-47262-6_1. ISBN 978-3-031-47262-6. 978-3-031-47262-6 ↩

  29. Mitchell, Melanie; Krakauer, David C. (2023-03-28). "The debate over understanding in AI's large language models". Proceedings of the National Academy of Sciences. 120 (13): e2215907120. arXiv:2210.13966. Bibcode:2023PNAS..12015907M. doi:10.1073/pnas.2215907120. ISSN 0027-8424. PMC 10068812. PMID 36943882. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10068812 ↩

  30. Saba, Walid S. (2023). "Stochastic LLMS do not Understand Language: Towards Symbolic, Explainable and Ontologically Based LLMS". In Almeida, João Paulo A.; Borbinha, José; Guizzardi, Giancarlo; Link, Sebastian; Zdravkovic, Jelena (eds.). Conceptual Modeling. Lecture Notes in Computer Science. Vol. 14320. Cham: Springer Nature Switzerland. pp. 3–19. arXiv:2309.05918. doi:10.1007/978-3-031-47262-6_1. ISBN 978-3-031-47262-6. 978-3-031-47262-6 ↩

  31. Saba, Walid S. (2023). "Stochastic LLMS do not Understand Language: Towards Symbolic, Explainable and Ontologically Based LLMS". In Almeida, João Paulo A.; Borbinha, José; Guizzardi, Giancarlo; Link, Sebastian; Zdravkovic, Jelena (eds.). Conceptual Modeling. Lecture Notes in Computer Science. Vol. 14320. Cham: Springer Nature Switzerland. pp. 3–19. arXiv:2309.05918. doi:10.1007/978-3-031-47262-6_1. ISBN 978-3-031-47262-6. 978-3-031-47262-6 ↩

  32. Saba, Walid S. (2023). "Stochastic LLMS do not Understand Language: Towards Symbolic, Explainable and Ontologically Based LLMS". In Almeida, João Paulo A.; Borbinha, José; Guizzardi, Giancarlo; Link, Sebastian; Zdravkovic, Jelena (eds.). Conceptual Modeling. Lecture Notes in Computer Science. Vol. 14320. Cham: Springer Nature Switzerland. pp. 3–19. arXiv:2309.05918. doi:10.1007/978-3-031-47262-6_1. ISBN 978-3-031-47262-6. 978-3-031-47262-6 ↩

  33. Fayyad, Usama M. (2023-05-26). "From Stochastic Parrots to Intelligent Assistants—The Secrets of Data and Human Interventions". IEEE Intelligent Systems. 38 (3): 63–67. doi:10.1109/MIS.2023.3268723. ISSN 1541-1672. https://ieeexplore.ieee.org/document/10148666 ↩

  34. Bender, Emily M.; Gebru, Timnit; McMillan-Major, Angelina; Mitchell, Margaret (2021). "On the Dangers of Stochastic Parrots: Can Language Models Be Too Big?". Proceedings of the 2021 ACM Conference on Fairness, Accountability, and Transparency. doi:10.1145/3442188.3445922. /wiki/Doi_(identifier) ↩

  35. Mitchell, Melanie; Krakauer, David C. (2023-03-28). "The debate over understanding in AI's large language models". Proceedings of the National Academy of Sciences. 120 (13): e2215907120. arXiv:2210.13966. Bibcode:2023PNAS..12015907M. doi:10.1073/pnas.2215907120. ISSN 0027-8424. PMC 10068812. PMID 36943882. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10068812 ↩

  36. Wang, Alex; Pruksachatkun, Yada; Nangia, Nikita; Singh, Amanpreet; Michael, Julian; Hill, Felix; Levy, Omer; Bowman, Samuel R. (2019-05-02). "SuperGLUE: A Stickier Benchmark for General-Purpose Language Understanding Systems". arXiv:1905.00537 [cs.CL]. /wiki/ArXiv_(identifier) ↩

  37. "GPT-4 Technical Report". 2023. arXiv:2303.08774. A bot will complete this citation soon. Click here to jump the queue /wiki/ArXiv_(identifier) ↩

  38. Mitchell, Melanie; Krakauer, David C. (2023-03-28). "The debate over understanding in AI's large language models". Proceedings of the National Academy of Sciences. 120 (13): e2215907120. arXiv:2210.13966. Bibcode:2023PNAS..12015907M. doi:10.1073/pnas.2215907120. ISSN 0027-8424. PMC 10068812. PMID 36943882. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10068812 ↩

  39. Pelley, Scott (8 October 2023). ""Godfather of Artificial Intelligence" Geoffrey Hinton on the promise, risks of advanced AI". CBS News. Retrieved 2 July 2025. https://www.cbsnews.com/news/geoffrey-hinton-ai-dangers-60-minutes-transcript/ ↩

  40. 60 Minutes (2023-10-09). "Godfather of AI" Geoffrey Hinton: The 60 Minutes Interview. Retrieved 2025-07-02 – via YouTube.{{cite AV media}}: CS1 maint: numeric names: authors list (link) https://www.youtube.com/watch?v=qrvK_KuIeJk ↩

  41. Morris, Ian (24 March 2024). "Inside the secret meeting where mathematicians struggled to outsmart AI". Scientific American. Retrieved 2 July 2025. https://www.scientificamerican.com/article/inside-the-secret-meeting-where-mathematicians-struggled-to-outsmart-ai/ ↩

  42. "GPT-4 Technical Report". 2023. arXiv:2303.08774. A bot will complete this citation soon. Click here to jump the queue /wiki/ArXiv_(identifier) ↩

  43. Li, Kenneth; Hopkins, Aspen K.; Bau, David; Viégas, Fernanda; Pfister, Hanspeter; Wattenberg, Martin (2023-02-27), Emergent World Representations: Exploring a Sequence Model Trained on a Synthetic Task, arXiv:2210.13382 /wiki/ArXiv_(identifier) ↩

  44. Li, Kenneth (2023-01-21). "Large Language Model: world models or surface statistics?". The Gradient. Retrieved 2024-04-04. https://thegradient.pub/othello/ ↩

  45. Jin, Charles; Rinard, Martin (2023-05-24), Evidence of Meaning in Language Models Trained on Programs, arXiv:2305.11169 /wiki/ArXiv_(identifier) ↩

  46. Schreiner, Maximilian (2023-08-11). "Grokking in machine learning: When Stochastic Parrots build models". the decoder. Retrieved 2024-05-25. https://the-decoder.com/grokking-in-machine-learning-when-stochastic-parrots-build-models/ ↩

  47. Choudhury, Sagnik Ray; Rogers, Anna; Augenstein, Isabelle (2022-09-15), Machine Reading, Fast and Slow: When Do Models "Understand" Language?, arXiv:2209.07430 /wiki/ArXiv_(identifier) ↩

  48. Geirhos, Robert; Jacobsen, Jörn-Henrik; Michaelis, Claudio; Zemel, Richard; Brendel, Wieland; Bethge, Matthias; Wichmann, Felix A. (2020-11-10). "Shortcut learning in deep neural networks". Nature Machine Intelligence. 2 (11): 665–673. arXiv:2004.07780. doi:10.1038/s42256-020-00257-z. ISSN 2522-5839. https://www.nature.com/articles/s42256-020-00257-z ↩

  49. Mitchell, Melanie; Krakauer, David C. (2023-03-28). "The debate over understanding in AI's large language models". Proceedings of the National Academy of Sciences. 120 (13): e2215907120. arXiv:2210.13966. Bibcode:2023PNAS..12015907M. doi:10.1073/pnas.2215907120. ISSN 0027-8424. PMC 10068812. PMID 36943882. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10068812 ↩

  50. Niven, Timothy; Kao, Hung-Yu (2019-09-16), Probing Neural Network Comprehension of Natural Language Arguments, arXiv:1907.07355 /wiki/ArXiv_(identifier) ↩

  51. Mitchell, Melanie; Krakauer, David C. (2023-03-28). "The debate over understanding in AI's large language models". Proceedings of the National Academy of Sciences. 120 (13): e2215907120. arXiv:2210.13966. Bibcode:2023PNAS..12015907M. doi:10.1073/pnas.2215907120. ISSN 0027-8424. PMC 10068812. PMID 36943882. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10068812 ↩

  52. Niven, Timothy; Kao, Hung-Yu (2019-09-16), Probing Neural Network Comprehension of Natural Language Arguments, arXiv:1907.07355 /wiki/ArXiv_(identifier) ↩