CoChat
Sign Up
Cited by 1Topic ModelingCognitive Science and Education ResearchPhilosophy and Theoretical Science

The DOI matches its Crossref record; 2 of the 2 references it cites were found in a registry or an index.

The Other Mind: How Language Models Exhibit Human Temporal Cognition

Open access
Li, Lingyu, Yao, Yang, Wang, Yixu, Li, Chunbo, Teng, Yan, Wang, Yingchun·2026·Proceedings of the AAAI Conference on Artificial Intelligence
DOI 10.1609/aaai.v40i42.40871
Open this paper in CoChat — free accountOpen PDF

Abstract

As Large Language Models (LLMs) continue to advance, they exhibit certain cognitive patterns similar to those of humans that are not directly specified in training data. This study investigates this phenomenon by focusing on temporal cognition in LLMs. Leveraging the similarity judgment task, we find that larger models spontaneously establish a subjective temporal reference point and adhere to the Weber-Fechner law, whereby the perceived distance logarithmically compresses as years recede from this reference point. To uncover the mechanisms behind this behavior, we conducted multiple analyses across neuronal, representational, and informational levels. We first identify a set of temporal-preferential neurons and find that this group exhibits minimal activation at the subjective reference point and implements a logarithmic coding scheme convergently found in biological systems. Probing representations of years reveals a hierarchical construction process, where years evolve from basic numerical values in shallow layers to abstract temporal orientation in deep layers. Finally, using pre-trained embedding models, we found that the training corpus itself possesses an inherent, non-linear temporal structure, which provides the raw material for the model's internal construction. In discussion, we propose an experientialist perspective for understanding these findings, where the LLMs' cognition is viewed as a subjective construction of the external world by its internal representational system. This nuanced perspective implies the potential emergence of alien cognitive frameworks that humans cannot intuitively predict, pointing toward a direction for AI alignment that focuses on guiding internal constructions.

Overview

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1609/aaai.v40i42.40871

Cites

2 of 2 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

  • At representational level, a hierarchical process was observed: shallow layers encode years primarily as objective numerical values, which are gradually reconstructed in deeper layers into an abstract temporal orientation relative to the reference point.

    “At the representational level, a hierarchical process was observed: shallow layers encode years primarily as objective numerical values, which are gradually reconstructed in deeper layers into an abstract temporal orientation relative to the reference point.”

    From Understanding large language models demands distinguishing human projection from machine cognition (2026) · cites this paper as [75]

  • At neuronal level, a subset of temporal-preferential neurons was identified, which implement a logarithmic coding scheme convergent with human brain neurons.

    “At the neuronal level, a subset of ‘temporal-preferential neurons’ was identified, which implement a logarithmic coding scheme convergent with human brain neurons.”

    From Understanding large language models demands distinguishing human projection from machine cognition (2026) · cites this paper as [75]

  • One recent study on LLM's temporal cognition provides evidence for extended experientialism.

    “One recent study on LLM’s temporal cognition provides evidence for this extended experientialism75.”

    From Understanding large language models demands distinguishing human projection from machine cognition (2026) · cites this paper as [75]

  • At information exposure level, the study analyzed semantic distribution of years using embedding models, revealing that training corpus itself possesses an inherent, non-linear temporal structure.

    “Finally, at the level of information exposure, the study analyzed the semantic distribution of years using embedding models, revealing that the training corpus itself possesses an inherent, non-linear temporal structure.”

    From Understanding large language models demands distinguishing human projection from machine cognition (2026) · cites this paper as [75]

  • Behaviorally, the study found that large models spontaneously establish a subjective temporal reference point and adhere to the Weber-Fechner law as humans do.

    “Behaviorally, the study found that large models spontaneously establish a subjective temporal reference point and adhere to the Weber-Fechner law as humans do.”

    From Understanding large language models demands distinguishing human projection from machine cognition (2026) · cites this paper as [75]

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Flagged first, then by citations

Research works printed but not linked: 59

  1. Alain, G.; and Bengio, Y. 2016. Understanding interme- diate layers using linear classifier probes. arXiv preprint arXiv:1610.01644. · arXiv
  2. Bai, Y.; Kadavath, S.; Kundu, S.; Askell, A.; Kernion, J.; Jones, A.; Chen, A.; Goldie, A.; Mirhoseini, A.; McKinnon, C.; et al. 2022. Constitutional ai: Harmlessness from ai feed- back. arXiv preprint arXiv:2212.08073. · arXiv
  3. Bengio, Y.; Cohen, M.; Fornasiere, D.; Ghosn, J.; Greiner, P.; MacDermott, M.; Mindermann, S.; Oberman, A.; Richardson, J.; Richardson, O.; et al. 2025a. Superintelli- gent agents pose catastrophic risks: Can scientist ai offer a safer path? arXiv preprint arXiv:2502.15657. · arXiv
  4. Bengio, Y.; Mindermann, S.; Privitera, D.; Besiroglu, T.; Bommasani, R.; Casper, S.; Choi, Y.; Fox, P.; Garfinkel, B.; Goldfarb, D.; et al. 2025b. International AI Safety Report. arXiv preprint arXiv:2501.17805. · arXiv
  5. Benjamini, Y.; and Hochberg, Y. 1995. Controlling the false discovery rate: a practical and powerful approach to multi- ple testing. Journal of the Royal statistical society: series B (Methodological), 57(1): 289-300.
  6. Berti, L.; Giorgi, F.; and Kasneci, G. 2025. Emergent Abil- ities in Large Language Models: A Survey. arXiv preprint arXiv:2503.05788. · arXiv
  7. Binz, M.; and Schulz, E. 2023. Using cognitive psychology to understand GPT-3. Proceedings of the National Academy of Sciences, 120(6): e2218523120.
  8. Bullmore, E.; and Sporns, O. 2009. Complex brain net- works: graph theoretical analysis of structural and functional systems. Nature reviews neuroscience, 10(3): 186-198.
  9. Chalmers, D. J. 2023. Could a large language model be con- scious? arXiv preprint arXiv:2303.07103. · arXiv
  10. Chen, J.; Wei, Z.; Ren, Z.; Li, Z.; and Zhang, J. 2025. LR 2 Bench: Evaluating Long-chain Reflective Reasoning Capabilities of Large Language Models via Constraint Sat- isfaction Problems. arXiv preprint arXiv:2502.17848. · arXiv
  11. Clark, A. 1998. Being there: Putting brain, body, and world together again. MIT press.
  12. Dalrymple, D.; Skalse, J.; Bengio, Y.; Russell, S.; Tegmark, M.; Seshia, S.; Omohundro, S.; Szegedy, C.; Goldhaber, B.; Ammann, N.; et al. 2024. Towards guaranteed safe ai: A framework for ensuring robust and reliable ai systems. arXiv preprint arXiv:2405.06624. · arXiv
  13. Davison, M. L.; and Sireci, S. G. 2000. Multidimensional scaling. In Handbook of applied multivariate statistics and mathematical modeling, 323-352. Elsevier.
  14. Dehaene, S. 2003. The neural basis of the Weber-Fechner law: a logarithmic mental number line. Trends in cognitive sciences, 7(4): 145-147.
  15. Demircan, C.; Saanum, T.; Jagadish, A. K.; Binz, M.; and Schulz, E. 2024. Sparse autoencoders reveal temporal dif- ference learning in large language models. arXiv preprint arXiv:2410.01280. · arXiv
  16. Dennett, D. C. 1993. Consciousness explained. Penguin uk.
  17. Faisal, A. A.; Selen, L. P.; and Wolpert, D. M. 2008. Noise in the nervous system. Nature reviews neuroscience, 9(4): 292-303.
  18. Field, D. J. 1994. What is the goal of sensory coding? Neural computation, 6(4): 559-601.
  19. Ganguli, D.; Lovitt, L.; Kernion, J.; Askell, A.; Bai, Y.; Ka- davath, S.; Mann, B.; Perez, E.; Schiefer, N.; Ndousse, K.; et al. 2022. Red teaming language models to reduce harms: Methods, scaling behaviors, and lessons learned. arXiv preprint arXiv:2209.07858. · arXiv
  20. Goldstein, A.; Ham, E.; Schain, M.; Nastase, S.; Zada, Z.; Dabush, A.; Aubrey, B.; Gazula, H.; Feder, A.; Doyle, W. K.; et al. 2023. The temporal structure of language processing in the human brain corresponds to the layered hierarchy of deep language models. arXiv preprint arXiv:2310.07106. · arXiv
  21. Goldstein, A.; Zada, Z.; Buchnik, E.; Schain, M.; Price, A.; Aubrey, B.; Nastase, S. A.; Feder, A.; Emanuel, D.; Cohen, A.; et al. 2020. Thinking ahead: spontaneous prediction in context as a keystone of language in humans and machines. BioRxiv, 2020-12.
  22. Greenblatt, R.; Denison, C.; Wright, B.; Roger, F.; MacDi- armid, M.; Marks, S.; Treutlein, J.; Belonax, T.; Chen, J.; Duvenaud, D.; et al. 2024. Alignment faking in large lan- guage models. arXiv preprint arXiv:2412.14093. · arXiv
  23. Guo, H.; Zhang, L.; Feng, X.; and Zheng, Q. 2024. A Re- view of the Application of Prompt Engineering in the Safety of Large Language Models. In Proceedings of the 2024 2nd International Conference on Information Education and Ar- tificial Intelligence, 424-430.
  24. Hahn, M.; and Goyal, N. 2023. A theory of emergent in-context learning as implicit structure induction. arXiv preprint arXiv:2303.07971. · arXiv
  25. Han, Y.; Xu, L.; Chen, S.; Zou, D.; and Lu, C. 2024. Beyond Surface Structure: A Causal Assessment of LLMs' Compre- hension Ability. arXiv preprint arXiv:2411.19456. · arXiv
  26. He, Q.; Zeng, J.; Huang, W.; Chen, L.; Xiao, J.; He, Q.; Zhou, X.; Liang, J.; and Xiao, Y. 2024. Can large language models understand real-world complex instructions? In Pro- ceedings of the AAAI Conference on Artificial Intelligence, volume 38, 18188-18196.
  27. Hinton, G. 2024. Will digital intelligence replace biological intelligence. Romanes Lecture, Oxford, UK, 19.
  28. Huben, R.; Cunningham, H.; Smith, L. R.; Ewart, A.; and Sharkey, L. 2023. Sparse autoencoders find highly inter- pretable features in language models. In The Twelfth Inter- national Conference on Learning Representations.
  29. Itzhak, I.; Stanovsky, G.; Rosenfeld, N.; and Belinkov, Y. 2024. Instructed to bias: Instruction-tuned language models exhibit emergent cognitive bias. Transactions of the Associ- ation for Computational Linguistics, 12: 771-785.
  30. Jones, C. R.; and Bergen, B. K. 2025. Large language mod- els pass the turing test. arXiv preprint arXiv:2503.23674. · arXiv
  31. Ku, A.; Campbell, D.; Bai, X.; Geng, J.; Liu, R.; Marjieh, R.; McCoy, R. T.; Nam, A.; Sucholutsky, I.; Veselovsky, V.; et al. 2025. Using the tools of cognitive science to under- stand large language models at different levels of analysis. arXiv preprint arXiv:2503.13401. · arXiv
  32. Kuo, M.; Zhang, J.; Ding, A.; Wang, Q.; DiValentin, L.; Bao, Y.; Wei, W.; Li, H.; and Chen, Y. 2025. H-cot: Hi- jacking the chain-of-thought safety reasoning mechanism to jailbreak large reasoning models, including openai o1/o3, deepseek-r1, and gemini 2.0 flash thinking. arXiv preprint arXiv:2502.12893. · arXiv
  33. Lakoff, G.; and Johnson, M. 2008. Metaphors we live by. University of Chicago press.
  34. Laughlin, S. 1981. A simple coding procedure enhances a neuron's information capacity. Zeitschrift für Natur- forschung c, 36(9-10): 910-912.
  35. Lee, J.; Chen, F.; Dua, S.; Cer, D.; Shanbhogue, M.; Naim, I.; Ábrego, G. H.; Li, Z.; Chen, K.; Vera, H. S.; et al. 2025. Gemini embedding: Generalizable embeddings from gem- ini. arXiv preprint arXiv:2503.07891. · arXiv
  36. Li, L.; Wang, Y.; Zhao, H.; Kong, S.; Teng, Y.; Li, C.; and Wang, Y. 2025. Reflection-Bench: Evaluating Epistemic Agency in Large Language Models. In Forty-second Inter- national Conference on Machine Learning.
  37. Liu, R.; Geng, J.; Wu, A. J.; Sucholutsky, I.; Lombrozo, T.; and Griffiths, T. L. 2024. Mind your step (by step): Chain- of-thought can reduce performance on tasks where thinking makes humans worse. arXiv preprint arXiv:2410.21333. · arXiv
  38. Marjieh, R.; Veselovsky, V.; Griffiths, T. L.; and Sucholut- sky, I. 2025. What is a Number, That a Large Language Model May Know It? arXiv preprint arXiv:2502.01540. · arXiv
  39. McCulloch, W. S.; and Pitts, W. 1943. A logical calculus of the ideas immanent in nervous activity. The bulletin of mathematical biophysics, 5: 115-133.
  40. Muennighoff, N.; Tazi, N.; Magne, L.; and Reimers, N. 2022. MTEB: Massive text embedding benchmark. arXiv preprint arXiv:2210.07316. OpenAI. 2024. text-embedding-3-large, https://platform.openai.com/docs/models/text-embedding- 3-large. Technical report. · arXiv
  41. Ouyang, L.; Wu, J.; Jiang, X.; Almeida, D.; Wainwright, C.; Mishkin, P.; Zhang, C.; Agarwal, S.; Slama, K.; Ray, A.; et al. 2022. Training language models to follow instructions with human feedback. Advances in neural information pro- cessing systems, 35: 27730-27744.
  42. Parr, T.; Pezzulo, G.; and Friston, K. J. 2022. Active infer- ence: the free energy principle in mind, brain, and behavior. MIT Press.
  43. Piantadosi, S. T.; Muller, D. C.; Rule, J. S.; Kaushik, K.; Gorenstein, M.; Leib, E. R.; and Sanford, E. 2024. Why con- cepts are (probably) vectors. Trends in Cognitive Sciences, 28(9): 844-856.
  44. Qin, Y.; Hu, S.; Lin, Y.; Chen, W.; Ding, N.; Cui, G.; Zeng, Z.; Zhou, X.; Huang, Y.; Xiao, C.; et al. 2024. Tool learning with foundation models. ACM Computing Surveys, 57(4): 1-40.
  45. Rosenblatt, F. 1958. The perceptron: a probabilistic model for information storage and organization in the brain. Psy- chological review, 65(6): 386.
  46. Shani, C.; Jurafsky, D.; LeCun, Y.; and Shwartz-Ziv, R. 2025. From tokens to thoughts: How LLMs and hu- mans trade compression for meaning. arXiv preprint arXiv:2505.17117. · arXiv
  47. Shepard, R. N. 1980. Multidimensional scaling, tree-fitting, and clustering. Science, 210(4468): 390-398.
  48. Strachan, J. W.; Albergo, D.; Borghini, G.; Pansardi, O.; Scaliti, E.; Gupta, S.; Saxena, K.; Rufo, A.; Panzeri, S.; Manzi, G.; et al. 2024. Testing theory of mind in large lan- guage models and humans. Nature Human Behaviour, 8(7): 1285-1295.
  49. Suri, G.; Slater, L. R.; Ziaee, A.; and Nguyen, M. 2024. Do large language models show decision heuristics similar to humans? A case study using GPT-3.5. Journal of Experi- mental Psychology: General, 153(4): 1066.
  50. Tang, Z.; and Kejriwal, M. 2024. Humanlike Cognitive Pat- terns as Emergent Phenomena in Large Language Models. arXiv preprint arXiv:2412.15501. · arXiv
  51. Tenenbaum, J. B.; and Griffiths, T. L. 2001. Generalization, similarity, and Bayesian inference. Behavioral and brain sciences, 24(4): 629-640.
  52. Valmeekam, K.; Marquez, M.; Olmo, A.; Sreedharan, S.; and Kambhampati, S. 2023. Planbench: An extensible benchmark for evaluating large language models on plan- ning and reasoning about change. Advances in Neural Infor- mation Processing Systems, 36: 38975-38987.
  53. Wei, J.; Wang, X.; Schuurmans, D.; Bosma, M.; Xia, F.; Chi, E.; Le, Q. V.; Zhou, D.; et al. 2022b. Chain-of- thought prompting elicits reasoning in large language mod- els. Advances in neural information processing systems, 35: 24824-24837.
  54. Wu, Z.; Peng, R.; Zheng, S.; Liu, Q.; Han, X.; Kwon, B. I.; Onizuka, M.; Tang, S.; and Xiao, C. 2024. Shall we team up: Exploring spontaneous cooperation of competing llm agents. arXiv preprint arXiv:2402.12327. · arXiv
  55. Xu, N.; Zhang, Q.; Du, C.; Luo, Q.; Qiu, X.; Huang, X.; and Zhang, M. 2025. Human-like conceptual represen- tations emerge from language prediction. arXiv preprint arXiv:2501.12547. · arXiv
  56. Yang, Z.; Dong, L.; Du, X.; Cheng, H.; Cambria, E.; Liu, X.; Gao, J.; and Wei, F. 2022. Language models as inductive reasoners. arXiv preprint arXiv:2212.10923. · arXiv
  57. Zhong, J.; Shen, W.; Li, Y.; Gao, S.; Lu, H.; Chen, Y.; Zhang, Y.; Zhou, W.; Gu, J.; and Zou, L. 2025. A comprehen- sive survey of reward models: Taxonomy, applications, chal- lenges, and future. arXiv preprint arXiv:2504.12328. · arXiv
  58. Zhu, J.-Q.; and Griffiths, T. L. 2024. Eliciting the priors of large language models using iterated in-context learning. arXiv preprint arXiv:2406.01860. · arXiv
  59. Zou, A.; Phan, L.; Chen, S.; Campbell, J.; Guo, P.; Ren, R.; Pan, A.; Yin, X.; Mazeika, M.; Dombrowski, A.-K.; et al. 2023. Representation engineering: A top-down approach to ai transparency. arXiv preprint arXiv:2310.01405. · arXiv

Cited by

Sorted by citations

Metadata

Authors
Li, L., Yao, Y., Wang, Y., Li, C., Teng, Y., & Wang, Y.
Affiliations
  • Shanghai Jiao Tong University (CN)
  • University of Hong Kong (HK)
  • Shanghai Artificial Intelligence Laboratory (CN)
ORCID
Venue
Proceedings of the AAAI Conference on Artificial Intelligence
Publisher
Association for the Advancement of Artificial Intelligence (AAAI)
Published
2026-03-14
Volume
40
Issue
42
Pages
35598-35607
ISSN
  • 2159-5399 (ISSN-L)
  • 2374-3468
DOI
10.1609/aaai.v40i42.40871
OpenAlex
W7139064763
Cited by
1
References
2
Citations by year
2026: 1
FWCI
8.94
Type
conference paper
Language
en
Open access
Locations
Proceedings of the AAAI Conference on Artificial Intelligence (publishedVersion)
Topics
  • Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
  • Life Sciences › Neuroscience › Cognitive Neuroscience › Cognitive Science and Education Research
  • Social Sciences › Arts and Humanities › Philosophy › Philosophy and Theoretical Science
Keywords
large language models, temporal cognition, Weber-Fechner law, similarity judgments, experientialism, AI alignment, emergent cognition

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review