---
title: "Are Language Models More Like Libraries or Like Librarians?"
description: "In Part II they present a new objection, the novel reference problem. 57 references, cited by 6 papers here."
authors: ["Harvey Lederman", "Kyle Mahowald"]
year: 2024
venue: "Transactions of the Association for Computational Linguistics"
source: "https://aclanthology.org/2024.tacl-1.60/"
doi: "10.1162/tacl_a_00690"
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/lederman-2024-are-language-models-more-like/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/lederman-2024-are-language-models-more-like/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2024](https://md.research.elamur.ai/free/en/papers/2024/page/11/) / Are Language Models More Like Libraries or Like Librarians? Bibliotechnism, the Novel Reference Problem, and the Attitudes of LLMs

# Are Language Models More Like Libraries or Like Librarians? Bibliotechnism, the Novel Reference Problem, and the Attitudes of LLMs

**Authors:** Harvey Lederman and [Kyle Mahowald](https://md.research.elamur.ai/free/en/authors/kyle-mahowald/) · **Year:** 2024 · **Venue:** [Transactions of the Association for Computational Linguistics](https://md.research.elamur.ai/free/en/venues/tacl/) ([Transactions of the Association for Computational Linguistics (TACL) 2024](https://md.research.elamur.ai/free/en/venues/tacl/2024/)) · **Publisher:** [The MIT Press](https://md.research.elamur.ai/free/en/publishers/the-mit-press/) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2024.tacl-1.60/) · [PDF](https://aclanthology.org/2024.tacl-1.60.pdf) · [DOI 10.1162/tacl\_a\_00690](https://doi.org/10.1162/tacl_a_00690) · [OpenAlex](https://openalex.org/W7133222288)

**Citations:** 7 citations (OpenAlex, 2026-10-14) · [6](https://md.research.elamur.ai/free/en/papers/lederman-2024-are-language-models-more-like/cited-by/) in our library, of the 149,439 papers whose bibliographies we read

## Summary
The paper asks whether large language models are best understood as cultural technologies, tools like photocopiers or libraries that only pass along human-made content, or as systems with beliefs, desires, and intentions. The authors call the first position, which extends Alison Gopnik's proposal, bibliotechnism. The study is purely philosophical and uses no experiments or datasets. In Part I they defend the view. They start from n-gram models as a simple case and move up to modern LLMs, arguing that even novel generated text can inherit its meaning from meaningful human text in the training data, with no revision to standard externalist theories of meaning. In Part II they present a new objection, the novel reference problem. LLMs can invent new names for newly created entities, and that reference cannot be borrowed from training data. Under interpretationism (Dennett, Davidson), a system has attitudes if attributing them explains its behavior well. On that view, the problem gives some evidence that LLMs have attitudes in a minimal sense. This claim implies nothing about consciousness, sentience, or intelligence.

## Key points
- "Bibliotechnism" combines the Greek words for book and skill. It holds two commitments: LLMs are cultural technologies, and LLMs lack beliefs, desires, and intentions.
- The core distinction is between basic meaning (tokens produced directly by an agent) and derivative meaning (tokens that inherit meaning, as in reprints or even accidental photocopies).
- The paper positions itself against Bender and Koller (2020), Piantadosi and Hill (2022), Mandelkern and Linzen (2023), and Cappelen and Dever (2021). Unlike these works, it argues that n-gram output can be meaningful without changing standard theories of meaning.
- It discusses other routes for bibliotechnists:
  - relying on Grice's "natural meaning";
  - denying that LLM output is meaningful at all;
  - denying meaning only to apparent cases of novel reference, an option the authors find somewhat appealing.
- Published in TACL vol. 12, pp. 1087–1103 (2024), DOI 10.1162/tacl_a_00690. The paper states it is distributed under CC-BY 4.0, which may allow broader reuse with attribution than assumed.

*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

- [The University of Texas at Austin](https://md.research.elamur.ai/free/en/universities/the-university-of-texas-at-austin/) — University, Austin, United States · 119 works · 57,950 citations

📚 Shelves (6): [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 17,450 works · [🤝 Social Sciences](https://md.research.elamur.ai/free/en/shelves/social-sciences/) · 1,954 works · [💭 Psychology](https://md.research.elamur.ai/free/en/shelves/psychology/) · 1,649 works · [💭 Experimental and Cognitive Psychology](https://md.research.elamur.ai/free/en/shelves/psychology/experimental-and-cognitive-psychology/) · 930 works · [🤝 Political Science and International Relations](https://md.research.elamur.ai/free/en/shelves/social-sciences/political-science-and-international-relations/) · 206 works · [🎭 History and Philosophy of Science](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/history-and-philosophy-of-science/) · 62 works

🧭 Topics (1): [🧠 Language models & pretraining](https://md.research.elamur.ai/free/en/topics/language-models/) · 3,894 works

## Cite

Cite as: Harvey Lederman and Kyle Mahowald. 2024. Are Language Models More Like Libraries or Like Librarians? Bibliotechnism, the Novel Reference Problem, and the Attitudes of LLMs. Transactions of the Association for Computational Linguistics.

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

```bibtex
@article{lederman2024are,
  title = {{Are Language Models More Like Libraries or Like Librarians? Bibliotechnism, the Novel Reference Problem, and the Attitudes of LLMs}},
  author = {Harvey Lederman and Kyle Mahowald},
  journal = {Transactions of the Association for Computational Linguistics},
  year = {2024},
  doi = {10.1162/tacl\_a\_00690},
  url = {https://doi.org/10.1162/tacl_a_00690}
}
```

- [← previous Ar-Spider: Text-to-SQL in Arabic](https://md.research.elamur.ai/free/en/papers/almohaimeed-2024-ar-spider-text-sql-arabic/)
- [next → CMM-Math: A Chinese Multimodal Math Dataset To Evaluate and Enhance the Mathematics Reasoning of Large Multimodal Models](https://md.research.elamur.ai/free/en/papers/liu-2024-cmm-math-chinese-multimodal-math/)
- [↑ back to papers of 2024](https://md.research.elamur.ai/free/en/papers/2024/page/11/)

## References

57 references, 17 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Yuntao Bai, Saurav Kadavath, Sandipan Kundu, Amanda Askell, Jackson Kernion, Andy Jones, Anna Chen, Anna Goldie, Azalia Mirhoseini, Cameron McKinnon, Carol Chen, Catherine Olsson, Christopher Olah, Danny Hernandez, Dawn Drain, Deep Ganguli, Dustin Li, Eli Tran-Johnson, Ethan Perez, Jamie Kerr, Jared… — [Constitutional AI: Harmlessness from AI Feedback](https://md.research.elamur.ai/free/en/papers/bai-2022-constitutional-ai-harmlessness-ai-feedback/)
2. Yonatan Belinkov. 2022. [Probing classifiers: Promises, shortcomings, and advances](https://md.research.elamur.ai/free/en/papers/belinkov-2022-probing-classifiers-promises-shortcomings-advances/). Computational Linguistics, 48(1):207–219. https://doi.org/10.1162/coli a 00422 [↗](https://doi.org/10.1162/coli)
3. Emily M. Bender and Alexander Koller. 2020. [Climbing towards NLU: On meaning, form, and understanding in the age of data](https://md.research.elamur.ai/free/en/papers/bender-2020-climbing-nlu-meaning-form-understanding/). In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 5185–5198, Online. Association for Computational Linguistics. [https://doi.org](https://doi.org) /1… [↗](https://doi.org)
4. Yonatan Bisk, Ari Holtzman, Jesse Thomason, Jacob Andreas, Yoshua Bengio, Joyce Chai, Mirella Lapata, Angeliki Lazaridou, Jonathan May, Aleksandr Nisnevich, Nicolas Pinto, and Joseph Turian. 2020. [Experience grounds language](https://md.research.elamur.ai/free/en/papers/bisk-2020-experience-grounds-language/). In Proceedings of the 2020 Conference on Empirical Methods in Natural Lang…
5. Sébastien Bubeck, Varun Chandrasekaran, Ronen Eldan, Johannes Gehrke, Eric Horvitz, Ece Kamar, Peter Lee, Yin Tat Lee, Yuanzhi Li, Scott Lundberg, Harsha Nori, Hamid Palangi, Marco Tulio Ribeiro, and Yi Zhang. 2023. [Sparks of artificial general intelligence: Early experiments with GPT-4](https://md.research.elamur.ai/free/en/papers/bubeck-2023-sparks-artificial-general-intelligence-early/). arXiv prep…
6. Tyler Burge. 1986. Individualism and psychology. The Philosophical Review, 95(1):3–45. https://doi.org/10.2307/2185131 — [doi:10.2307/2185131](https://doi.org/10.2307/2185131) [↗](https://doi.org/10.2307/2185131)
7. Patrick Butlin, Robert Long, Eric Elmoznino, Yoshua Bengio, Jonathan Birch, Axel Constant, George Deane, Stephen M. Fleming, Chris Frith, Xu Ji, Ryota Kanai, Colin Klein, Grace Lindsay, Matthias Michel, Liad Mudrik, Megan A. K. Peters, Eric Schwitzgebel, Jonathan Simon, and Rufin VanRullen. 2023. Co… — [arXiv:2308.08708](https://arxiv.org/abs/2308.08708) [find](https://scholar.google.com/scholar?q=Patrick+Butlin%2C+Robert+Long%2C+Eric+Elmoznino%2C+Yoshua+Bengio%2C+Jonathan+Birch%2C+Axel+Constant%2C+George+Deane%2C+Stephen+M%2E+Fleming%2C+Chris+Frith%2C+Xu+Ji%2C+Ryota+Kanai%2C+Colin+Klein%2C+Grace+Lindsay%2C+Matthias+Miche)
8. Herman Cappelen and Josh Dever. 2021. Making AI Intelligible: Philosophical Foundations. Oxford University Press. https://doi.org/10.1093/oso/9780192894724.001.0001 — [doi:10.1093/oso/9780192894724.001.0001](https://doi.org/10.1093/oso/9780192894724.001.0001) [↗](https://doi.org/10.1093/oso/9780192894724.001.0001)
9. David J. Chalmers. 2023. Could a large language model be conscious? arXiv preprint arXiv:2303.07103. [find](https://scholar.google.com/scholar?q=David+J%2E+Chalmers%2E+2023%2E+Could+a+large+language+model+be+conscious%3F+arXiv+preprint+arXiv%3A2303%2E07103%2E)
10. Ted Chiang. 2023. ChatGPT is a blurry JPEG of the web. New Yorker. [find](https://scholar.google.com/scholar?q=Ted+Chiang%2E+2023%2E+ChatGPT+is+a+blurry+JPEG+of+the+web%2E+New+Yorker%2E)
11. Dimitri Coelho Mollo and Raphaël Millière. 2023. [The vector grounding problem](https://md.research.elamur.ai/free/en/papers/mollo-2023-vector-grounding-problem/). arXiv preprint arXiv:2304.01481.
12. Donald Davidson. 1973. Radical interpretation. Dialectica, pages 313–328. https://doi.org/10.1111/j.1746-8361.1973.tb00623.x Donald Davidson. 1986. A coherence theory of truth and knowledge. Epistemology: An anthology, pages 124–133. — [doi:10.1111/j.1746-8361.1973.tb00623.x](https://doi.org/10.1111/j.1746-8361.1973.tb00623.x) [↗](https://doi.org/10.1111/j.1746-8361.1973.tb00623.x)
13. Louis de Rosset. 2020. Reference switch and bad dubbings. [https://www.uvm.edu/](https://www.uvm.edu/) ˜lderosse/madagascar.pdf Daniel C. Dennett. 1971. Intentional systems. The Journal of Philosophy, 68(4):87–106. https://doi.org/10.2307/2025382 — [doi:10.2307/2025382](https://doi.org/10.2307/2025382) [↗](https://www.uvm.edu/)
14. Daniel C. Dennett. 1989. The Intentional Stance. MIT Press. https://doi.org/10.1017/S0140525X00058611 [↗](https://doi.org/10.1017/S0140525X00058611)
15. Keith S. Donnellan. 1970. Proper names and identifying descriptions. Synthese, 21:335–358. https://doi.org/10.1007/BF00484804 — [doi:10.1007/bf00484804](https://doi.org/10.1007/bf00484804) [↗](https://doi.org/10.1007/BF00484804)
16. Yanai Elazar, Nora Kassner, Shauli Ravfogel, Abhilasha Ravichander, Eduard Hovy, Hinrich Schütze, and Yoav Goldberg. 2021. Measuring and improving consistency in pretrained language models. Transactions of the Association for Computational Linguistics, 9:1012–1031. https://doi.org/10.1162/tacl a 00… [↗](https://doi.org/10.1162/tacl)
17. Gareth Evans. 1973. The causal theory of names. Proceedings of the Aristotelian Society, Supplementary Volumes, 47:187–225. https://doi.org/10.1093/aristoteliansupp/47.1.187 — [doi:10.1093/aristoteliansupp](https://doi.org/10.1093/aristoteliansupp) [↗](https://doi.org/10.1093/aristoteliansupp/47.1.187)
18. Michael C. Frank. 2023. Baby steps in evaluating the capacities of large language models. Nature Reviews Psychology, 2(8):451–452. https://doi.org/10.1038/s44159-023 -00211-x Peter Thomas Geach. 1969. The perils of Pauline. The Review of Metaphysics, pages 287–300. — [doi:10.1038/s44159-023](https://doi.org/10.1038/s44159-023) [↗](https://doi.org/10.1038/s44159-023)
19. Ariel Goldstein and Gabriel Stanovsky. 2024. Do zombies understand? A choose-your-own-adventure exploration of machine cognition. arXiv preprint arXiv:2403.00499. [find](https://scholar.google.com/scholar?q=Ariel+Goldstein+and+Gabriel+Stanovsky%2E+2024%2E+Do+zombies+understand%3F+A+choose%2Dyour%2Down%2Dadventure+exploration+of+machine+cognition%2E+arXiv+preprint+arXiv%3A2403%2E00499%2E)
20. Alison Gopnik. 2022a. Children, creativity, and the real key to intelligence. Observer. [https://www.psychologicalscience.org/observer/children-creativity](https://www.psychologicalscience.org/observer/children-creativity) -intelligence Alison Gopnik. 2022b. What AI still doesn’t know how to do. The Wall Street Journal. https://www.wsj.com/articles/what -ai-still-do… [↗](https://www.psychologicalscience.org/observer/children-creativity)
21. H. Paul Grice. 1957. Meaning. The Philosophical Review, 66(3):377–388. https://doi.org/10.2307/2182440 — [doi:10.2307/2182440](https://doi.org/10.2307/2182440) [↗](https://doi.org/10.2307/2182440)
22. 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 the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume…
23. Peter Hase, Mona Diab, Asli Celikyilmaz, Xian Li, Zornitsa Kozareva, Veselin Stoyanov, Mohit Bansal, and Srinivasan Iyer. 2023. [Methods for measuring, updating, and visualizing factual beliefs in language models](https://md.research.elamur.ai/free/en/papers/hase-2023-methods-measuring-updating-visualizing-factual/). In Proceedings of the 17th Conference of the European Chapter of the Association for Co…
24. Jussi Haukioja. 2020. Semantic burden-shifting and temporal externalism. Inquiry, 63(9–10):919–929. https://doi.org/10 .1080/0020174X.2020.1805704 [find](https://scholar.google.com/scholar?q=Jussi+Haukioja%2E+2020%2E+Semantic+burden%2Dshifting+and+temporal+externalism%2E+Inquiry%2C+63%289%E2%80%9310%29%3A919%E2%80%93929%2E+https%3A%2F%2Fdoi%2Eorg%2F10+%2E1080%2F0020174X%2E2020%2E1805704)
25. Henry Jackman. 1999. We live forwards but understand backwards: Linguistic practices and future behavior. Pacific Philosophical Quarterly, 80(2):157–177. https://doi.org/10 .1111/1468-0114.00078 [find](https://scholar.google.com/scholar?q=Henry+Jackman%2E+1999%2E+We+live+forwards+but+understand+backwards%3A+Linguistic+practices+and+future+behavior%2E+Pacific+Philosophical+Quarterly%2C+80%282%29%3A157%E2%80%93177%2E+https%3A%2F%2Fdoi%2Eorg%2F10+%2E1111%2F1468%2D0114%2E00078)
26. Henry Jackman. 2005. Temporal externalism and our ordinary linguistic practices. Pacific Philosophical Quarterly, 86(3):365–380. https://doi.org/10.1111/j.1468-0114.2005.00232.x — [doi:10.1111/j.1468-0114.2005.00232.x](https://doi.org/10.1111/j.1468-0114.2005.00232.x) [↗](https://doi.org/10.1111/j.1468-0114.2005.00232.x)
27. Myeongjun Jang and Thomas Lukasiewicz. 2023. Consistency analysis of ChatGPT. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 15970–15985, Singapore. Association for Computational Linguistics. https://doi.org/10.18653/v1/2023.emnlp-main.991 [↗](https://doi.org/10.18653/v1/2023.emnlp-main.991)
28. Najoung Kim and Sebastian Schuster. 2023. [Entity tracking in language models](https://md.research.elamur.ai/free/en/papers/kim-2023-entity-tracking-language-models/). In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 3835–3855, Toronto, Canada. Association for Computational Linguistics. https://doi.org/10 .18653/v1/…
29. Saul A. Kripke. 1980. Naming and necessity. In Semantics of Natural Language, pages 253–355. Springer. https://doi.org/10.1007/978 -94-010-2557-7 9 — [doi:10.1007/978](https://doi.org/10.1007/978) [↗](https://doi.org/10.1007/978)
30. Brenden M. Lake and Gregory L. Murphy. 2023. Word meaning in minds and machines. Psychological Review, 130(2):401. https://doi.org/10.1037/rev0000297, PubMed: 34292021 — [doi:10.1037/rev0000297](https://doi.org/10.1037/rev0000297) [↗](https://doi.org/10.1037/rev0000297)
31. Yair Lakretz, German Kruszewski, Theo Desbordes, Dieuwke Hupkes, Stanislas Dehaene, and Marco Baroni. 2019. [The emergence of number and syntax units in LSTM language models](https://md.research.elamur.ai/free/en/papers/lakretz-2019-emergence-number-syntax-units-lstm/). In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human La…
32. Benjamin A. Levinstein and Daniel A. Herrmann. 2024. Still no lie detector for language models: Probing empirical and conceptual roadblocks. Philosophical Studies, pages 1–27. https://doi.org/10.1007/s11098-023-02094-3 [↗](https://doi.org/10.1007/s11098-023-02094-3)
33. Aitor Lewkowycz, Anders Andreassen, David Dohan, Ethan Dyer, Henryk Michalewski, Vinay Ramasesh, Ambrose Slone, Cem Anil, Imanol Schlag, Theo Gutman-Solo, et al. 2022. [Solving quantitative reasoning problems with language models](https://md.research.elamur.ai/free/en/papers/lewkowycz-2022-solving-quantitative-reasoning-problems-language/). Advances in Neural Information Processing Systems, 35:3843–3857.
34. 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, Published online March 19, 2024. https://doi.org/10 .1016/j.tics.2024.01.011, PubMed: 38508911 [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)
35. Fintan Mallory. 2023. Fictionalism about chatbots. Ergo an Open Access Journal of Philosophy, 10. https://doi.org/10.3998/ergo.4668 [↗](https://doi.org/10.3998/ergo.4668)
36. Matthew Mandelkern and Tal Linzen. 2023. Do language models refer? arXiv preprint arXiv:2308.05576. — [arXiv:2308.05576](https://arxiv.org/abs/2308.05576) [find](https://scholar.google.com/scholar?q=Matthew+Mandelkern+and+Tal+Linzen%2E+2023%2E+Do+language+models+refer%3F+arXiv+preprint+arXiv%3A2308%2E05576%2E+%E2%80%94+%5BarXiv%3A2308%2E05576%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F2308%2E05576%29)
37. David Marr. 1982. Vision: A Computational Investigation into the Human Representation and Processing of Visual Information. W. H. Freeman & Company. [find](https://scholar.google.com/scholar?q=David+Marr%2E+1982%2E+Vision%3A+A+Computational+Investigation+into+the+Human+Representation+and+Processing+of+Visual+Information%2E+W%2E+H%2E+Freeman+%26+Company%2E)
38. John McCarthy. 1979. Ascribing Mental Qualities to Machines. Stanford University. Computer Science Department. [find](https://scholar.google.com/scholar?q=John+McCarthy%2E+1979%2E+Ascribing+Mental+Qualities+to+Machines%2E+Stanford+University%2E+Computer+Science+Department%2E)
39. R. Thomas McCoy, Paul Smolensky, Tal Linzen, Jianfeng Gao, and Asli Celikyilmaz. 2023. [How much do language models copy from their training data? Evaluating linguistic novelty in text generation using RAVEN](https://md.research.elamur.ai/free/en/papers/mccoy-2023-how-much-do-language-models/). Transactions of the Association for Computational Linguistics, 11:652–670. https://doi.org/1…
40. Tom McCoy, Ellie Pavlick, and Tal Linzen. 2019. [Right for the wrong reasons: Diagnosing syntactic heuristics in natural language inference](https://md.research.elamur.ai/free/en/papers/mccoy-2019-right-wrong-reasons-diagnosing-syntactic/). In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 3428–3448, Florence, Italy. Association for Computational Ling…
41. Eliot Michaelson. 2023. The vagaries of reference. Ergo an Open Access Journal of Philosophy, 9. https://doi.org/10.3998/ergo.3115 [↗](https://doi.org/10.3998/ergo.3115)
42. Raphaël Millière and Cameron Buckner. 2024. A Philosophical introduction to language models– Part I: Continuity with classic debates. arXiv preprint arXiv:2401.03910. — [arXiv:2401.03910](https://arxiv.org/abs/2401.03910) [find](https://scholar.google.com/scholar?q=Raphae%CC%88l+Millie%CC%80re+and+Cameron+Buckner%2E+2024%2E+A+Philosophical+introduction+to+language+models%E2%80%93+Part+I%3A+Continuity+with+classic+debates%2E+arXiv+preprint+arXiv%3A2401%2E03910%2E+%E2%80%94+%5BarXiv%3A2401%2E03910%5D%28https%3A%2F%2Far)
43. Melanie Mitchell and David C. Krakauer. 2023. The debate over understanding in AI’s large language models. Proceedings of the National Academy of Sciences, 120(13):e2215907120. https://doi.org/10.1073/pnas.2215907120, PubMed: 36943882 — [doi:10.1073/pnas.2215907120](https://doi.org/10.1073/pnas.2215907120) [↗](https://doi.org/10.1073/pnas.2215907120)
44. Ryan M. Nefdt. 2023. Are machines radically con-textualist? Mind & Language, 38(3):750–771. https://doi.org/10.1111/mila.12429 — [doi:10.1111/mila.12429](https://doi.org/10.1111/mila.12429) [↗](https://doi.org/10.1111/mila.12429)
45. Xenia Ohmer, Elia Bruni, and Dieuwke Hupkes. 2024. [From form(s) to meaning: Probing the semantic depths of language models using multisense consistency](https://md.research.elamur.ai/free/en/papers/ohmer-2024-form-s-meaning-probing-semantic/). arXiv preprint arXiv: 2404.12145.
46. Gary Ostertag. 2023. Meaning by courtesy: LLM-generated texts and the illusion of content. The American Journal of Bioethics, 23(10):91–93. https://doi.org/10.1080/15265161.2023.2249851, PubMed: 37812115 [↗](https://doi.org/10.1080/15265161.2023.2249851)
47. Long Ouyang, Jeff Wu, Xu Jiang, Diogo Almeida, Carroll L. Wainwright, Pamela Mishkin, Chong Zhang, Sandhini Agarwal, Katarina Slama, Alex Ray, John Schulman, Jacob Hilton, Fraser Kelton, Luke Miller, Maddie Simens, Amanda Askell, Peter Welinder, Paul Christiano, Jan Leike, and Ryan Lowe. 2022. [Train…](https://md.research.elamur.ai/free/en/papers/ouyang-2022-training-language-models-follow-instructions/)
48. Roma Patel and Ellie Pavlick. 2022. Mapping language models to grounded conceptual spaces. In The Tenth International Conference on Learning Representations, ICLR 2022, Virtual Event, April 25–29, 2022. OpenReview.net. [find](https://scholar.google.com/scholar?q=Roma+Patel+and+Ellie+Pavlick%2E+2022%2E+Mapping+language+models+to+grounded+conceptual+spaces%2E+In+The+Tenth+International+Conference+on+Learning+Representations%2C+ICLR+2022%2C+Virtual+Event%2C+April+25%E2%80%9329%2C+202)
49. Steven T. Piantadosi and Felix Hill. 2022. Meaning without reference in large language models. arXiv preprint arXiv:2208.02957. — [arXiv:2208.02957](https://arxiv.org/abs/2208.02957) [find](https://scholar.google.com/scholar?q=Steven+T%2E+Piantadosi+and+Felix+Hill%2E+2022%2E+Meaning+without+reference+in+large+language+models%2E+arXiv+preprint+arXiv%3A2208%2E02957%2E+%E2%80%94+%5BarXiv%3A2208%2E02957%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F2208%2E02957%29)
50. Hilary Putnam. 1975. The meaning of ‘‘meaning’’. In Minnesota Studies in the Philosophy of Science, Volume 7: Language, Mind, and Knowledge, pages 131–193. University of Minnesota Press, Minneapolis. [find](https://scholar.google.com/scholar?q=Hilary+Putnam%2E+1975%2E+The+meaning+of+%E2%80%98%E2%80%98meaning%E2%80%99%E2%80%99%2E+In+Minnesota+Studies+in+the+Philosophy+of+Science%2C+Volume+7%3A+Language%2C+Mind%2C+and+Knowledge%2C+pages+131%E2%80%93193%2E+University+of+Minnesota+Press%2C+Minneapolis%2E)
51. Eric Schwitzgebel. 2023. Belief. In Edward N. Zalta and Uri Nodelman, editors, The Stanford Encyclopedia of Philosophy, Winter 2023 edition. Metaphysics Research Lab, Stanford University. [find](https://scholar.google.com/scholar?q=Eric+Schwitzgebel%2E+2023%2E+Belief%2E+In+Edward+N%2E+Zalta+and+Uri+Nodelman%2C+editors%2C+The+Stanford+Encyclopedia+of+Philosophy%2C+Winter+2023+edition%2E+Metaphysics+Research+Lab%2C+Stanford+University%2E)
52. Cosma Shalizi. 2023. [‘‘Attention’’, ’’Transformers’’, in Neural Network ‘‘Large Language Models’’](https://md.research.elamur.ai/free/en/papers/shanahan-2023-role-play-large-language-models/). [https://bactra.org/notebooks/nn-attention-and-transformers.html](https://bactra.org/notebooks/nn-attention-and-transformers.html) Murray Shanahan, Kyle McDonell, and Laria Reynolds. 2023. Role play with large language models. Nature, 623(7987):493–498. https://doi.o… [↗](https://bactra.org/notebooks/nn-attention-and-transformers.html)
53. Lisa Miracchi Titus. 2024. Does ChatGPT have semantic understanding? Cognitive Systems Research, 83(101174):1–13. https://doi.org/10.1016/j.cogsys.2023.101174 — [doi:10.1016/j.cogsys.2023.101174](https://doi.org/10.1016/j.cogsys.2023.101174) [↗](https://doi.org/10.1016/j.cogsys.2023.101174)
54. Sean Trott, Cameron Jones, Tyler Chang, James Michaelov, and Benjamin Bergen. 2023. Do large language models know what humans know? Cognitive Science, 47(7):e13309. https://doi.org/10.1111/cogs.13309, PubMed: 37401923 — [doi:10.1111/cogs.13309](https://doi.org/10.1111/cogs.13309) [↗](https://doi.org/10.1111/cogs.13309)
55. Zhengxuan Wu, Atticus Geiger, Thomas Icard, Christopher Potts, and Noah Goodman. 2024. [Interpretability at scale: Identifying causal mechanisms in alpaca](https://md.research.elamur.ai/free/en/papers/wu-2023-interpretability-scale-identifying-causal-mechanisms/). Advances in Neural Information Processing Systems, 36.
56. Ilker Yildirim and L. A. Paul. 2024. From task structures to world models: What do LLMs know? Trends in Cognitive Sciences, 28(5):404–415. https://doi.org/10.1016/j.tics.2024.02.008, PubMed: 38443199 [↗](https://doi.org/10.1016/j.tics.2024.02.008)
57. Eunice Yiu, Eliza Kosoy, and Alison Gopnik. 2023. Transmission versus truth, imitation versus innovation: What children can do that large language and language-and-vision models cannot (yet). Perspectives on Psychological Science, page 17456916231201401. https://doi.org/10.1177/17456916231201401, P… [↗](https://doi.org/10.1177/17456916231201401)

*Updated 2 November 2026*