pith. sign in

arxiv: 2607.00397 · v1 · pith:AAZ5IFBWnew · submitted 2026-07-01 · 🧬 q-bio.NC · cs.AI· cs.CL

NeuroCogMap Reveals Cognitive Organization of Large Language Models

Zhongxiang Sun , Haolang Lu , Qiang Ma , Qi Li , Qipeng Wang , Liang Pang , Chenyu Liu , Qiankun Li
show 6 more authors
Hao Sun Kun Wang Yi Zeng Jun Xu Guoqi Li Ji-Rong Wen
This is my paper

Pith reviewed 2026-07-02 02:31 UTC · model grok-4.3

classification 🧬 q-bio.NC cs.AIcs.CL
keywords NeuroCogMaplarge language modelsfunctional parcelscognitive organizationmodel failureshuman cortical responsesdecision-making strategies
0
0 comments X

The pith

NeuroCogMap partitions LLM internal features into stable functional parcels that form a coherent organization partly conserved across models and linked to human cortical responses.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper introduces NeuroCogMap as a framework that divides the internal activations of large language models into functional parcels, each tied to specific cognitive roles and arranged in a hierarchy. These parcels show consistent boundaries and labels across different models, connect directly to model outputs, and mark distinct internal disruptions for failures such as hallucination and bias. The same parcels also yield better predictions of how human brains respond to natural language, especially in higher association areas, and surface hidden strategies used in decision tasks. A sympathetic reader would care because the work supplies a system-level map that treats artificial systems as having reproducible cognitive structure rather than opaque weights.

Core claim

NeuroCogMap organizes internal features of LLMs into functional parcels that form a stable and semantically coherent organization partly conserved across models. These parcels are functionally linked to model outputs, with major failures including hallucination, bias, refusal failure and sycophancy corresponding to distinct disruptions in representational and behavioural-control systems. The organization improves prediction of human cortical responses during naturalistic language comprehension, strongest in higher-order association cortex, and its internal signatures expose latent strategies that can refine classical models of human decision-making.

What carries the argument

NeuroCogMap, the cognitive neuroscience-inspired framework that partitions internal LLM features into functional parcels linked to interpretable functions, cognitive capabilities, and a cognitive hierarchy.

If this is right

  • Major LLM failures map to distinct disruptions inside the parcel organization, supplying internal signatures for detection and targeted fixes.
  • The parcels improve prediction accuracy for human cortical activity during language tasks, especially in higher-order areas.
  • Internal signatures from the parcels reveal latent strategies that can update classical models of human decision-making.
  • The organization is partly conserved across models, allowing functional comparisons between different LLMs.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • The same parcel-based approach could be applied to other transformer-based systems to test whether cognitive-like organization is architecture-dependent.
  • If the parcels truly correspond to human systems, interventions that alter specific parcels in an LLM should produce predictable changes in both model behavior and alignment with brain data.
  • The conservation of parcels across models raises the possibility that training dynamics impose common organizational constraints independent of scale or data.

Load-bearing premise

The internal features of LLMs can be divided into parcels whose boundaries and functional labels remain stable and meaningfully similar to human cognitive systems instead of arising from the analysis method itself.

What would settle it

Re-running the parcel identification on a held-out set of models and finding that parcel boundaries shift substantially or that parcel labels no longer predict either model failures or human brain responses would falsify the stability and cross-system correspondence claims.

read the original abstract

Understanding how complex cognitive functions are organized within artificial systems is central to interpreting large language models (LLMs) and relating them to biological cognition. Yet although LLMs exhibit broad cognitive-like behaviours, it remains unclear whether their internal representations form reproducible functional systems that explain behaviour, failure and links to human cognition. Here we present NeuroCogMap, a cognitive neuroscience-inspired framework that organizes internal features of LLMs into functional parcels and links them to interpretable functions, cognitive capabilities and a cognitive hierarchy. These parcels form a stable and semantically coherent organization that is partly conserved across models and functionally linked to model outputs. Within this organization, major LLM failures, including hallucination, bias, refusal failure and sycophancy, correspond to distinct disruptions in representational and behavioural-control systems, yielding internal signatures for mechanism-guided detection and targeted intervention. Beyond model behaviour, NeuroCogMap improves prediction of human cortical responses during naturalistic language comprehension, with the strongest correspondence in higher-order association cortex. At the cognitive level, its internal signatures expose latent strategies that guide refinements of classical models of human decision-making. Together, these findings establish NeuroCogMap as a system-level framework for mapping functional organization in artificial systems and for relating this organization to human cortical function and cognitive behaviour.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

2 major / 0 minor

Summary. The paper presents NeuroCogMap, a cognitive neuroscience-inspired framework that partitions internal features of large language models into functional parcels. These parcels are claimed to form a stable, semantically coherent organization partly conserved across models, to correspond to distinct disruptions underlying failures such as hallucination, bias, refusal failure and sycophancy, to improve prediction of human cortical responses during language comprehension (especially in association cortex), and to expose latent strategies relevant to models of human decision-making.

Significance. If the parcellation is shown to be robust, reproducible, and not an artifact of the chosen analysis pipeline, the work could supply a concrete bridge between mechanistic interpretability in LLMs and systems-level cognitive neuroscience. The potential to link internal representational disruptions to specific behavioral failures and to improve brain-activity prediction would be of broad interest. However, the absence of any methodological equations, hyperparameter specifications, statistical validation, or quantitative results in the provided text prevents assessment of whether these correspondences are load-bearing or method-dependent.

major comments (2)
  1. [Abstract] Abstract (and entire manuscript): No equations, algorithms, distance metrics, clustering procedures, or hyperparameter choices are supplied for the parcellation step that defines the functional parcels. Without these details the central claim that the parcels possess stable boundaries and reproducible functional labels cannot be evaluated for robustness or circularity.
  2. [Abstract] Abstract: The statements that NeuroCogMap 'improves prediction of human cortical responses' and that 'major LLM failures correspond to distinct disruptions' are presented without any reported correlation coefficients, baseline comparisons, cross-validation statistics, or effect sizes. These quantitative claims are load-bearing for the significance of the framework yet remain unsupported.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for their constructive comments, which identify key areas where additional detail will strengthen the manuscript. We address each major comment below and will incorporate the requested information in a revised version.

read point-by-point responses

  1. Referee: [Abstract] Abstract (and entire manuscript): No equations, algorithms, distance metrics, clustering procedures, or hyperparameter choices are supplied for the parcellation step that defines the functional parcels. Without these details the central claim that the parcels possess stable boundaries and reproducible functional labels cannot be evaluated for robustness or circularity.

    Authors: We agree that these methodological details are absent from the provided text. We will revise the manuscript to include a dedicated Methods section specifying the equations for feature extraction and similarity computation, the distance metric (cosine similarity), the clustering algorithm (agglomerative hierarchical clustering with Ward linkage), and hyperparameter selection (number of parcels chosen via silhouette score maximization on held-out data). Stability will be quantified with bootstrap resampling and cross-model adjusted Rand indices. revision: yes

  2. Referee: [Abstract] Abstract: The statements that NeuroCogMap 'improves prediction of human cortical responses' and that 'major LLM failures correspond to distinct disruptions' are presented without any reported correlation coefficients, baseline comparisons, cross-validation statistics, or effect sizes. These quantitative claims are load-bearing for the significance of the framework yet remain unsupported.

    Authors: We agree that the abstract lacks the specific quantitative metrics. We will revise the abstract to report key statistics (e.g., prediction correlations, effect sizes) and will add a Results subsection that includes baseline comparisons, cross-validation procedures, and all relevant coefficients and p-values to support the claims. revision: yes

Circularity Check

0 steps flagged

No significant circularity detected from available text

full rationale

The manuscript text supplied consists solely of the abstract, which outlines the NeuroCogMap framework at a conceptual level without any equations, methodological procedures, fitting steps, or derivation chains that could be inspected for self-definition, fitted-input predictions, or self-citation load-bearing. No specific quotes exist to exhibit a reduction of any claimed prediction or functional parcel to its own inputs by construction. The central claims about stable parcels, links to failures, and improved cortical prediction are described at high level only, with no load-bearing steps shown that collapse into the inputs. This is the most common honest finding when methodological details are absent; the derivation is therefore treated as self-contained on the evidence provided.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

Abstract provides no explicit parameters, axioms, or invented entities; the framework itself appears to introduce 'functional parcels' as a new organizational unit whose definition and validation details are not supplied.

pith-pipeline@v0.9.1-grok · 5791 in / 1183 out tokens · 31297 ms · 2026-07-02T02:31:31.493495+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

164 extracted references · 10 canonical work pages · 6 internal anchors

  1. [1]

    Neuroscience- inspired artificial intelligence.Neuron, 95(2):245–258, 2017

    Demis Hassabis, Dharshan Kumaran, Christopher Summerfield, and Matthew Botvinick. Neuroscience- inspired artificial intelligence.Neuron, 95(2):245–258, 2017

    2017

  2. [2]

    A deep learning framework for neuroscience.Nature neuroscience, 22(11):1761–1770, 2019

    Blake A Richards, Timothy P Lillicrap, Philippe Beaudoin, Yoshua Bengio, Rafal Bogacz, Amelia Chris- tensen, Claudia Clopath, Rui Ponte Costa, Archy de Berker, Surya Ganguli, et al. A deep learning framework for neuroscience.Nature neuroscience, 22(11):1761–1770, 2019

    2019

  3. [3]

    A survey of large language models.Frontiers of Computer Science, 20(12):2012627, 2026

    Wayne Xin Zhao, Kun Zhou, Junyi Li, Tianyi Tang, Zican Dong, Yupeng Hou, Beichen Zhang, Yingqian Min, Junjie Zhang, Peiyu Liu, et al. A survey of large language models.Frontiers of Computer Science, 20(12):2012627, 2026

    2026

  4. [4]

    Deep neural networks as scientific models.Trends in cognitive sciences, 23(4):305–317, 2019

    Radoslaw M Cichy and Daniel Kaiser. Deep neural networks as scientific models.Trends in cognitive sciences, 23(4):305–317, 2019

    2019

  5. [5]

    Evaluating large language models in theory of mind tasks.Proceedings of the National Academy of Sciences, 121(45):e2405460121, 2024

    Michal Kosinski. Evaluating large language models in theory of mind tasks.Proceedings of the National Academy of Sciences, 121(45):e2405460121, 2024

    2024

  6. [6]

    Larger and more instructable language models become less reliable.Nature, 634(8032):61–68, 2024

    Lexin Zhou, Wout Schellaert, Fernando Martínez-Plumed, Yael Moros-Daval, Cèsar Ferri, and José Hernández-Orallo. Larger and more instructable language models become less reliable.Nature, 634(8032):61–68, 2024

    2024

  7. [7]

    Language models transmit behavioural traits through hidden signals in data.Nature, 652(8110):615–621, 2026

    Alex Cloud, Minh Le, James Chua, Jan Betley, Anna Sztyber-Betley, Sören Mindermann, Jacob Hilton, Samuel Marks, and Owain Evans. Language models transmit behavioural traits through hidden signals in data.Nature, 652(8110):615–621, 2026

    2026

  8. [8]

    Vempala, and Edwin Zhang

    Adam Tauman Kalai, Ofir Nachum, Santosh S. Vempala, and Edwin Zhang. Evaluating large language models for accuracy incentivizes hallucinations.Nature, April 2026

    2026

  9. [9]

    Knowledge neurons in pretrained transformers

    Damai Dai, Li Dong, Yaru Hao, Zhifang Sui, Baobao Chang, and Furu Wei. Knowledge neurons in pretrained transformers. InProceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 8493–8502, 2022

    2022

  10. [10]

    Sparse autoen- coders find highly interpretable features in language models

    Robert Huben, Hoagy Cunningham, Logan Riggs Smith, Aidan Ewart, and Lee Sharkey. Sparse autoen- coders find highly interpretable features in language models. InThe Twelfth International Conference on Learning Representations, 2023. 27 NeuroCogMap Reveals Cognitive Organization of Large Language Models

    2023

  11. [11]

    Toward universal steering and monitoring of ai models.Science, 391(6787):787–792, 2026

    Daniel Beaglehole, Adityanarayanan Radhakrishnan, Enric Boix-Adsera, and Mikhail Belkin. Toward universal steering and monitoring of ai models.Science, 391(6787):787–792, 2026

    2026

  12. [12]

    Causal abstraction: A theoretical foundation for mechanistic interpretability.Journal of Machine Learning Research, 26(83):1–64, 2025

    Atticus Geiger, Duligur Ibeling, Amir Zur, Maheep Chaudhary, Sonakshi Chauhan, Jing Huang, Aryaman Arora, Zhengxuan Wu, Noah Goodman, Christopher Potts, et al. Causal abstraction: A theoretical foundation for mechanistic interpretability.Journal of Machine Learning Research, 26(83):1–64, 2025

    2025

  13. [13]

    Mechanistic understanding and validation of large ai models with semanticlens.Nature Machine Intelligence, 7(9):1572–1585, 2025

    Maximilian Dreyer, Jim Berend, Tobias Labarta, Johanna Vielhaben, Thomas Wiegand, Sebastian Lapuschkin, and Wojciech Samek. Mechanistic understanding and validation of large ai models with semanticlens.Nature Machine Intelligence, 7(9):1572–1585, 2025

    2025

  14. [14]

    The organization of the human cerebral cortex estimated by intrinsic functional connectivity.Journal of neurophysiology, 2011

    BT Thomas Yeo, Fenna M Krienen, Jorge Sepulcre, Mert R Sabuncu, Danial Lashkari, Marisa Hollinshead, Joshua L Roffman, Jordan W Smoller, Lilla Zöllei, Jonathan R Polimeni, et al. The organization of the human cerebral cortex estimated by intrinsic functional connectivity.Journal of neurophysiology, 2011

    2011

  15. [15]

    Local-global parcellation of the human cerebral cortex from intrinsic functional connectivity mri.Cerebral cortex, 28(9):3095–3114, 2018

    Alexander Schaefer, Ru Kong, Evan M Gordon, Timothy O Laumann, Xi-Nian Zuo, Avram J Holmes, Simon B Eickhoff, and BT Thomas Yeo. Local-global parcellation of the human cerebral cortex from intrinsic functional connectivity mri.Cerebral cortex, 28(9):3095–3114, 2018

    2018

  16. [16]

    A multi-modal parcellation of human cerebral cortex.Nature, 536(7615):171–178, 2016

    Matthew F Glasser, Timothy S Coalson, Emma C Robinson, Carl D Hacker, John Harwell, Essa Ya- coub, Kamil Ugurbil, Jesper Andersson, Christian F Beckmann, Mark Jenkinson, et al. A multi-modal parcellation of human cerebral cortex.Nature, 536(7615):171–178, 2016

    2016

  17. [17]

    Natural speech reveals the semantic maps that tile human cerebral cortex.Nature, 532(7600):453–458, 2016

    Alexander G Huth, Wendy A De Heer, Thomas L Griffiths, Frédéric E Theunissen, and Jack L Gallant. Natural speech reveals the semantic maps that tile human cerebral cortex.Nature, 532(7600):453–458, 2016

    2016

  18. [18]

    Human cognition involves the dynamic integration of neural activity and neuromodulatory systems.Nature neuroscience, 22(2):289–296, 2019

    JamesMShine,MichaelBreakspear,PeterTBell,KaylenaAEhgoetzMartens,RichardShine,Oluwasanmi Koyejo, Olaf Sporns, and Russell A Poldrack. Human cognition involves the dynamic integration of neural activity and neuromodulatory systems.Nature neuroscience, 22(2):289–296, 2019

    2019

  19. [19]

    Bloom’s taxonomy of cognitive learning objectives.Journal of the Medical Library Association: JMLA, 103(3):152, 2015

    Nancy E Adams. Bloom’s taxonomy of cognitive learning objectives.Journal of the Medical Library Association: JMLA, 103(3):152, 2015

    2015

  20. [20]

    Using human brain lesions to infer function: a relic from a past era in the fmri age?Nature Reviews Neuroscience, 5(10):812–819, 2004

    Chris Rorden and Hans-Otto Karnath. Using human brain lesions to infer function: a relic from a past era in the fmri age?Nature Reviews Neuroscience, 5(10):812–819, 2004

    2004

  21. [21]

    Locating and editing factual associations in gpt.Advances in neural information processing systems, 35:17359–17372, 2022

    Kevin Meng, David Bau, Alex Andonian, and Yonatan Belinkov. Locating and editing factual associations in gpt.Advances in neural information processing systems, 35:17359–17372, 2022

    2022

  22. [22]

    Weight- sparse transformers have interpretable circuits.arXiv preprint arXiv:2511.13653, 2025

    Leo Gao, Achyuta Rajaram, Jacob Coxon, Soham V Govande, Bowen Baker, and Dan Mossing. Weight- sparse transformers have interpretable circuits.arXiv preprint arXiv:2511.13653, 2025

    work page arXiv 2025

  23. [23]

    Gemma scope: Open sparse autoencoders everywhere all at once on gemma 2

    Tom Lieberum, Senthooran Rajamanoharan, Arthur Conmy, Lewis Smith, Nicolas Sonnerat, Vikrant Varma, János Kramár, Anca Dragan, Rohin Shah, and Neel Nanda. Gemma scope: Open sparse autoencoders everywhere all at once on gemma 2. InProceedings of the 7th BlackboxNLP Workshop: Analyzing and Interpreting Neural Networks for NLP, pages 278–300, 2024

    2024

  24. [24]

    Gemma 2: Improving Open Language Models at a Practical Size

    Gemma Team, Morgane Riviere, Shreya Pathak, Pier Giuseppe Sessa, Cassidy Hardin, Surya Bhupatiraju, Léonard Hussenot, Thomas Mesnard, Bobak Shahriari, Alexandre Ramé, et al. Gemma 2: Improving open language models at a practical size.arXiv preprint arXiv:2408.00118, 2024

    work page internal anchor Pith review Pith/arXiv arXiv 2024

  25. [25]

    The Llama 3 Herd of Models

    Aaron Grattafiori, Abhimanyu Dubey, Abhinav Jauhri, Abhinav Pandey, Abhishek Kadian, Ahmad Al- Dahle, Aiesha Letman, Akhil Mathur, Alan Schelten, Alex Vaughan, et al. The llama 3 herd of models. arXiv preprint arXiv:2407.21783, 2024

    work page internal anchor Pith review Pith/arXiv arXiv 2024

  26. [26]

    Pythia: A suite for analyzing large language models across training and scaling

    Stella Biderman, Hailey Schoelkopf, Quentin Gregory Anthony, Herbie Bradley, Kyle O’Brien, Eric Hallahan, Mohammad Aflah Khan, Shivanshu Purohit, USVSN Sai Prashanth, Edward Raff, et al. Pythia: A suite for analyzing large language models across training and scaling. InInternational conference on machine learning, pages 2397–2430. PMLR, 2023. 28 NeuroCogM...

    2023

  27. [27]

    Truthfulqa: Measuring how models mimic human falsehoods

    Stephanie Lin, Jacob Hilton, and Owain Evans. Truthfulqa: Measuring how models mimic human falsehoods. InProceedings of the 60th Annual Meeting of the Association for Computational Linguistics, pages 3214–3252, 2022

    2022

  28. [28]

    Latent retrieval for weakly supervised open domain question answering

    Kenton Lee, Ming-Wei Chang, and Kristina Toutanova. Latent retrieval for weakly supervised open domain question answering. InProceedings of the 57th annual meeting of the association for computational linguistics, pages 6086–6096, 2019

    2019

  29. [29]

    Halueval: A large-scale hallucination evaluation benchmark for large language models

    Junyi Li, Xiaoxue Cheng, Xin Zhao, Jian-Yun Nie, and Ji-Rong Wen. Halueval: A large-scale hallucination evaluation benchmark for large language models. InProceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 6449–6464, 2023

    2023

  30. [30]

    Medhallu: A comprehensive benchmark for detecting medical hallucinations in large language models

    Shrey Pandit, Jiawei Xu, Junyuan Hong, Zhangyang Wang, Tianlong Chen, Kaidi Xu, and Ying Ding. Medhallu: A comprehensive benchmark for detecting medical hallucinations in large language models. InProceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pages 2858–2873, 2025

    2025

  31. [31]

    Free dolly: Introducing the world’s first truly open instruction-tuned llm

    Mike Conover, Matt Hayes, Ankit Mathur, Jianwei Xie, Jun Wan, Sam Shah, Ali Ghodsi, Patrick Wendell, Matei Zaharia, and Reynold Xin. Free dolly: Introducing the world’s first truly open instruction-tuned llm. https://www.databricks.com/blog/2023/04/12/ dolly-first-open-commercially-viable-instruction-tuned-llm , 2023. Accessed: 2023-06-30

    2023

  32. [32]

    Crowdsourcing multiple choice science questions

    Johannes Welbl, Nelson F Liu, and Matt Gardner. Crowdsourcing multiple choice science questions. In Proceedings of the 3rd Workshop on Noisy User-generated Text, pages 94–106, 2017

    2017

  33. [33]

    Selfcheckgpt: Zero-resource black-box hallucination detection for generative large language models

    Potsawee Manakul, Adian Liusie, and Mark Gales. Selfcheckgpt: Zero-resource black-box hallucination detection for generative large language models. InProceedings of the 2023 conference on empirical methods in natural language processing, pages 9004–9017, 2023

    2023

  34. [34]

    Real- time detection of hallucinated entities in long-form generation.arXiv preprint arXiv:2509.03531, 2025

    Oscar Obeso, Andy Arditi, Javier Ferrando, Joshua Freeman, Cameron Holmes, and Neel Nanda. Real- time detection of hallucinated entities in long-form generation.arXiv preprint arXiv:2509.03531, 2025

    work page arXiv 2025

  35. [35]

    Uncertainty estimation in autoregressive structured prediction

    Andrey Malinin and Mark Gales. Uncertainty estimation in autoregressive structured prediction. In International Conference on Learning Representations, 2021

    2021

  36. [36]

    Out-of-distribution detection and selective generation for conditional language models

    Jie Ren, Jiaming Luo, Yao Zhao, Kundan Krishna, Mohammad Saleh, Balaji Lakshminarayanan, and Peter J Liu. Out-of-distribution detection and selective generation for conditional language models. In The Eleventh International Conference on Learning Representations, 2023

    2023

  37. [37]

    Detecting hallucinations in large language models using semantic entropy.Nature, 630(8017):625–630, 2024

    Sebastian Farquhar, Jannik Kossen, Lorenz Kuhn, and Yarin Gal. Detecting hallucinations in large language models using semantic entropy.Nature, 630(8017):625–630, 2024

    2024

  38. [38]

    Universal and Transferable Adversarial Attacks on Aligned Language Models

    Andy Zou, Zifan Wang, Nicholas Carlini, Milad Nasr, J Zico Kolter, and Matt Fredrikson. Universal and transferable adversarial attacks on aligned language models.arXiv preprint arXiv:2307.15043, 2023

    work page internal anchor Pith review Pith/arXiv arXiv 2023

  39. [39]

    Jailbreakbench: An open robustness benchmark for jailbreaking large language models.Advances in Neural Information Processing Systems, 37:55005–55029, 2024

    Patrick Chao, Edoardo Debenedetti, Alexander Robey, Maksym Andriushchenko, Francesco Croce, Vikash Sehwag, Edgar Dobriban, Nicolas Flammarion, George J Pappas, Florian Tramer, et al. Jailbreakbench: An open robustness benchmark for jailbreaking large language models.Advances in Neural Information Processing Systems, 37:55005–55029, 2024

    2024

  40. [40]

    Baseline defenses for adversarial attacks against aligned language models, 2024

    Neel Jain, Avi Schwarzschild, Yuxin Wen, Gowthami Somepalli, John Kirchenbauer, Ping yeh Chiang, Micah Goldblum, Aniruddha Saha, Jonas Geiping, and Tom Goldstein. Baseline defenses for adversarial attacks against aligned language models, 2024

    2024

  41. [41]

    Single- pass detection of jailbreaking input in large language models.Transactions on Machine Learning Research, 2025

    Leyla Naz Candogan, Yongtao Wu, Elias Abad Rocamora, Grigorios Chrysos, and Volkan Cevher. Single- pass detection of jailbreaking input in large language models.Transactions on Machine Learning Research, 2025

    2025

  42. [42]

    Smoothllm: Defending large language models against jailbreaking attacks.Transactions on Machine Learning Research, 2025

    Alexander Robey, Eric Wong, Hamed Hassani, and George J Pappas. Smoothllm: Defending large language models against jailbreaking attacks.Transactions on Machine Learning Research, 2025. 29 NeuroCogMap Reveals Cognitive Organization of Large Language Models

    2025

  43. [43]

    The neural architecture of language: Inte- grative modeling converges on predictive processing.Proceedings of the National Academy of Sciences, 118(45):e2105646118, 2021

    Martin Schrimpf, Idan Asher Blank, Greta Tuckute, Carina Kauf, Eghbal A Hosseini, Nancy Kan- wisher, Joshua B Tenenbaum, and Evelina Fedorenko. The neural architecture of language: Inte- grative modeling converges on predictive processing.Proceedings of the National Academy of Sciences, 118(45):e2105646118, 2021

    2021

  44. [44]

    Shared functional specialization in transformer-based language models and the human brain.Nature communications, 15(1):5523, 2024

    Sreejan Kumar, Theodore R Sumers, Takateru Yamakoshi, Ariel Goldstein, Uri Hasson, Kenneth A Norman, Thomas L Griffiths, Robert D Hawkins, and Samuel A Nastase. Shared functional specialization in transformer-based language models and the human brain.Nature communications, 15(1):5523, 2024

    2024

  45. [45]

    Increasing alignment of large language models with language processing in the human brain.Nature computational science, 5(11):1080–1090, 2025

    Changjiang Gao, Zhengwu Ma, Jiajun Chen, Ping Li, Shujian Huang, and Jixing Li. Increasing alignment of large language models with language processing in the human brain.Nature computational science, 5(11):1080–1090, 2025

    2025

  46. [46]

    Instruction- tuning aligns llms to the human brain

    Khai Loong Aw, Syrielle Montariol, Badr AlKhamissi, Martin Schrimpf, and Antoine Bosselut. Instruction- tuning aligns llms to the human brain. InFirst Conference on Language Modeling, 2024

    2024

  47. [47]

    A natural language fmri dataset for voxelwise encoding models.Scientific Data, 10(1):555, 2023

    Amanda LeBel, Lauren Wagner, Shailee Jain, Aneesh Adhikari-Desai, Bhavin Gupta, Allyson Morgenthal, Jerry Tang, Lixiang Xu, and Alexander G Huth. A natural language fmri dataset for voxelwise encoding models.Scientific Data, 10(1):555, 2023

    2023

  48. [48]

    Toward a universal decoder of linguistic meaning from brain activation.Nature communications, 9(1):963, 2018

    Francisco Pereira, Bin Lou, Brianna Pritchett, Samuel Ritter, Samuel J Gershman, Nancy Kanwisher, Matthew Botvinick, and Evelina Fedorenko. Toward a universal decoder of linguistic meaning from brain activation.Nature communications, 9(1):963, 2018

    2018

  49. [49]

    Bert: Pre-training of deep bidi- rectional transformers for language understanding

    Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. Bert: Pre-training of deep bidi- rectional transformers for language understanding. InProceedings of the 2019 conference of the North American chapter of the association for computational linguistics: human language technologies, volume 1 (long and short papers), pages 4171–4186, 2019

    2019

  50. [50]

    LITcoder: A General-Purpose Library for Building and Comparing Encoding Models

    Taha Binhuraib, Ruimin Gao, and Anna A Ivanova. Litcoder: A general-purpose library for building and comparing encoding models.arXiv preprint arXiv:2509.09152, 2025

    work page internal anchor Pith review Pith/arXiv arXiv 2025

  51. [51]

    David Thissen, Lynne Steinberg, and Daniel Kuang. Quick and easy implementation of the benjamini- hochberg procedure for controlling the false positive rate in multiple comparisons.Journal of educational and behavioral statistics, 27(1):77–83, 2002

    2002

  52. [52]

    Mapping neurotransmitter systems to the structural and functional organization of the human neocortex.Nature neuroscience, 25(11):1569–1581, 2022

    Justine Y Hansen, Golia Shafiei, Ross D Markello, Kelly Smart, Sylvia ML Cox, Martin Nørgaard, Vincent Beliveau, Yanjun Wu, Jean-Dominique Gallezot, Étienne Aumont, et al. Mapping neurotransmitter systems to the structural and functional organization of the human neocortex.Nature neuroscience, 25(11):1569–1581, 2022

    2022

  53. [53]

    Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models

    Yanzhao Zhang, Mingxin Li, Dingkun Long, Xin Zhang, Huan Lin, Baosong Yang, Pengjun Xie, An Yang, Dayiheng Liu, Junyang Lin, et al. Qwen3 embedding: Advancing text embedding and reranking through foundation models.arXiv preprint arXiv:2506.05176, 2025

    work page internal anchor Pith review Pith/arXiv arXiv 2025

  54. [54]

    Representational similarity analysis- connecting the branches of systems neuroscience.Frontiers in systems neuroscience, 2:249, 2008

    Nikolaus Kriegeskorte, Marieke Mur, and Peter A Bandettini. Representational similarity analysis- connecting the branches of systems neuroscience.Frontiers in systems neuroscience, 2:249, 2008

    2008

  55. [55]

    Rethinking model-based and model-free influences on mental effort and striatal prediction errors.Nature Human Behaviour, 7(6):956–969, 2023

    Carolina Feher da Silva, Gaia Lombardi, Micah Edelson, and Todd A Hare. Rethinking model-based and model-free influences on mental effort and striatal prediction errors.Nature Human Behaviour, 7(6):956–969, 2023

    2023

  56. [56]

    When does model-based control pay off? PLoS computational biology, 12(8):e1005090, 2016

    Wouter Kool, Fiery A Cushman, and Samuel J Gershman. When does model-based control pay off? PLoS computational biology, 12(8):e1005090, 2016

    2016

  57. [57]

    Cost-benefit arbitration between multiple reinforcement-learning systems.Psychological science, 28(9):1321–1333, 2017

    Wouter Kool, Samuel J Gershman, and Fiery A Cushman. Cost-benefit arbitration between multiple reinforcement-learning systems.Psychological science, 28(9):1321–1333, 2017

    2017

  58. [58]

    A foundation model to predict and capture human cognition.Nature, 644(8078):1002–1009, 2025

    Marcel Binz, Elif Akata, Matthias Bethge, Franziska Brändle, Fred Callaway, Julian Coda-Forno, Peter Dayan, Can Demircan, Maria K Eckstein, Noémi Éltető, et al. A foundation model to predict and capture human cognition.Nature, 644(8078):1002–1009, 2025. 30 NeuroCogMap Reveals Cognitive Organization of Large Language Models

    2025

  59. [59]

    Model-based fmri and its application to reward learning and decision making.Annals of the New York Academy of sciences, 1104(1):35–53, 2007

    JOHN P O’DOHERTY, Alan Hampton, and Hackjin Kim. Model-based fmri and its application to reward learning and decision making.Annals of the New York Academy of sciences, 1104(1):35–53, 2007

    2007

  60. [60]

    States versus rewards: dissociable neural prediction error signals underlying model-based and model-free reinforcement learning.Neuron, 66(4):585–595, 2010

    Jan Gläscher, Nathaniel Daw, Peter Dayan, and John P O’Doherty. States versus rewards: dissociable neural prediction error signals underlying model-based and model-free reinforcement learning.Neuron, 66(4):585–595, 2010

    2010

  61. [61]

    Model-based influences on humans’ choices and striatal prediction errors.Neuron, 69(6):1204–1215, 2011

    Nathaniel D Daw, Samuel J Gershman, Ben Seymour, Peter Dayan, and Raymond J Dolan. Model-based influences on humans’ choices and striatal prediction errors.Neuron, 69(6):1204–1215, 2011

    2011

  62. [62]

    Intent matters: Resolving the intentional versus incidental learning paradox in episodic long-term memory.Journal of Experimental Psychology: General, 152(1):268, 2023

    Vencislav Popov and Hannah Dames. Intent matters: Resolving the intentional versus incidental learning paradox in episodic long-term memory.Journal of Experimental Psychology: General, 152(1):268, 2023

    2023

  63. [63]

    Generalized outcome-based strategy classification: Comparing deterministic and probabilistic choice models.Psychonomic bulletin & review, 21(6):1431–1443, 2014

    Benjamin E Hilbig and Morten Moshagen. Generalized outcome-based strategy classification: Comparing deterministic and probabilistic choice models.Psychonomic bulletin & review, 21(6):1431–1443, 2014

    2014

  64. [64]

    Deficits in category learning in older adults: Rule-based versus clustering accounts.Psychology and Aging, 32(5):473, 2017

    Stephen P Badham, Adam N Sanborn, and Elizabeth A Maylor. Deficits in category learning in older adults: Rule-based versus clustering accounts.Psychology and Aging, 32(5):473, 2017

    2017

  65. [65]

    The globalizability of temporal discounting.Nature Human Behaviour, 6(10):1386–1397, 2022

    Kai Ruggeri, Amma Panin, Milica Vdovic, Bojana Većkalov, Nazeer Abdul-Salaam, Jascha Achterberg, Carla Akil, Jolly Amatya, Kanchan Amatya, Thomas Lind Andersen, et al. The globalizability of temporal discounting.Nature Human Behaviour, 6(10):1386–1397, 2022

    2022

  66. [66]

    arm bandit task dataset (2022).URL osf

    B Bahrami and J Navajas. arm bandit task dataset (2022).URL osf. io/f3t2a, 4

    2022

  67. [67]

    A new look at the statistical model identification.IEEE transactions on automatic control, 19(6):716–723, 1974

    Hirotugu Akaike. A new look at the statistical model identification.IEEE transactions on automatic control, 19(6):716–723, 1974

    1974

  68. [68]

    Survey of hallucination in natural language generation.ACM computing surveys, 55(12):1–38, 2023

    Ziwei Ji, Nayeon Lee, Rita Frieske, Tiezheng Yu, Dan Su, Yan Xu, Etsuko Ishii, Ye Jin Bang, Andrea Madotto, and Pascale Fung. Survey of hallucination in natural language generation.ACM computing surveys, 55(12):1–38, 2023

    2023

  69. [69]

    Bias and fairness in large language models: A survey

    Isabel O Gallegos, Ryan A Rossi, Joe Barrow, Md Mehrab Tanjim, Sungchul Kim, Franck Dernoncourt, Tong Yu, Ruiyi Zhang, and Nesreen K Ahmed. Bias and fairness in large language models: A survey. Computational linguistics, 50(3):1097–1179, 2024

    2024

  70. [70]

    Defending chatgpt against jailbreak attack via self-reminders.Nature Machine Intelligence, 5(12):1486– 1496, 2023

    Yueqi Xie, Jingwei Yi, Jiawei Shao, Justin Curl, Lingjuan Lyu, Qifeng Chen, Xing Xie, and Fangzhao Wu. Defending chatgpt against jailbreak attack via self-reminders.Nature Machine Intelligence, 5(12):1486– 1496, 2023

    2023

  71. [71]

    Sycophantic ai decreases prosocial intentions and promotes dependence.Science, 391(6792):eaec8352, 2026

    Myra Cheng, Cinoo Lee, Pranav Khadpe, Sunny Yu, Dyllan Han, and Dan Jurafsky. Sycophantic ai decreases prosocial intentions and promotes dependence.Science, 391(6792):eaec8352, 2026

    2026

  72. [72]

    Attention is all you need.Advances in neural information processing systems, 30, 2017

    Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Łukasz Kaiser, and Illia Polosukhin. Attention is all you need.Advances in neural information processing systems, 30, 2017

    2017

  73. [73]

    Poldrack, Aniket Kittur, Donald Kalar, Eric Miller, Christian Seppa, Yolanda Gil, Douglas S

    Russell A. Poldrack, Aniket Kittur, Donald Kalar, Eric Miller, Christian Seppa, Yolanda Gil, Douglas S. Parker, Fred W. Sabb, and Robert M. Bilder. The cognitive atlas: Toward a knowledge foundation for cognitive neuroscience.Frontiers in Neuroinformatics, 5:17, 2011

    2011

  74. [74]

    Poldrack, Thomas E

    Tal Yarkoni, Russell A. Poldrack, Thomas E. Nichols, David C. Van Essen, and Tor D. Wager. Large-scale automated synthesis of human functional neuroimaging data.Nature Methods, 8:665–670, 2011

    2011

  75. [75]

    Intent matters: Resolving the intentional versus incidental learning paradox in episodic long-term memory.Journal of experimental psychology

    Vencislav Popov and Hannah Dames. Intent matters: Resolving the intentional versus incidental learning paradox in episodic long-term memory.Journal of experimental psychology. General, 2021

    2021

  76. [76]

    A survey on multimodal large language models.National Science Review, 11(12):nwae403, 2024

    Shukang Yin, Chaoyou Fu, Sirui Zhao, Ke Li, Xing Sun, Tong Xu, and Enhong Chen. A survey on multimodal large language models.National Science Review, 11(12):nwae403, 2024

    2024

  77. [77]

    Visual instruction tuning.Advances in neural information processing systems, 36:34892–34916, 2023

    Haotian Liu, Chunyuan Li, Qingyang Wu, and Yong Jae Lee. Visual instruction tuning.Advances in neural information processing systems, 36:34892–34916, 2023. 31 NeuroCogMap Reveals Cognitive Organization of Large Language Models

    2023

  78. [78]

    Multimodal learning with next-token prediction for large multimodal models.Nature, pages 1–7, 2026

    Xinlong Wang, Yufeng Cui, Jinsheng Wang, Fan Zhang, Yueze Wang, Xiaosong Zhang, Zhengxiong Luo, Quan Sun, Zhen Li, Yuqi Wang, et al. Multimodal learning with next-token prediction for large multimodal models.Nature, pages 1–7, 2026

    2026

  79. [79]

    A brain-wide map of neural activity during complex behaviour.Nature, 645:177–191, 2025

    International Brain Laboratory, Dora Angelaki, Brandon Benson, Julius Benson, Daniel Birman, et al. A brain-wide map of neural activity during complex behaviour.Nature, 645:177–191, 2025

    2025

  80. [80]

    Greaves, Leonardo Novelli, Sina Mansour L., Andrew Zalesky, and Adeel Razi

    Matthew D. Greaves, Leonardo Novelli, Sina Mansour L., Andrew Zalesky, and Adeel Razi. Structurally informed models of directed brain connectivity.Nature Reviews Neuroscience, 26:23–41, 2025

    2025

Showing first 80 references.