mlsanityData to 14 Oct 2026

Large Language Models Show Signs of Alignment with Human Neurocognition During Abstract Reasoning

arXiv 2508.10057 ↗First posted 12 Aug 2025q-bio.NC cs.AI cs.CLcited by 2

On the map: LLM reasoning → Reasoning benchmarks and evaluation

Abstract (arXiv)

This study investigates whether large language models (LLMs) mirror human neurocognition during abstract reasoning. We compared the performance and neural representations of human participants with those of eight open-source LLMs on an abstract-pattern-completion task. We leveraged pattern type differences in task performance and in fixation-related potentials (FRPs) as recorded by electroencephalography (EEG) during the task. Our findings indicate that only the largest tested LLMs (~70 billion parameters) achieve human-comparable accuracy, with Qwen-2.5-72B and DeepSeek-R1-70B also showing similarities with the human pattern-specific difficulty profile. Critically, every LLM tested forms representations that distinctly cluster the abstract pattern categories within their intermediate layers, although the strength of this clustering scales with their performance on the task. Moderate positive correlations were observed between the representational geometries of task-optimal LLM layers and human frontal FRPs. These results consistently diverged from comparisons with other EEG measures (response-locked ERPs and resting EEG), suggesting a potential shared representational space for abstract patterns. This indicates that LLMs might mirror human brain mechanisms in abstract reasoning, offering preliminary evidence of shared principles between biological and artificial intelligence.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning. Builds on 29 of its 72 references that are in the map. First posted on arXiv 12 Aug 2025.

Builds on

29 of 72 references.

Closest ancestors · 8

Same direction, newest first

  1. 2025Truly Assessing Fluid Intelligence of Large Language Models through Dynamic Reasoning Evaluation3 Jun
  2. 2025Do Large Language Models Think Like the Brain? Sentence-Level Evidences from Layer-Wise Embeddings and fMRI28 May
  3. 2025Navigating Semantic Relations: Challenges for Language Models in Abstract Common-Sense Reasoning19 Feb
  4. 2024Evaluating the Robustness of Analogical Reasoning in Large Language Models21 Nov
  5. 2024LLMs as Models for Analogical Reasoning19 Jun
  6. 2024Easy Problems That LLMs Get Wrong30 May
  7. 2023ARN: Analogical Reasoning on Narratives2 Oct
  8. 2023Large Language Models Are Not Strong Abstract Reasoners31 May

Other references · 21

  1. 2022Locating and Editing Factual Associations in GPTcited by 2,691
  2. 2023Sparks of Artificial General Intelligence: Early experiments with GPT-4cited by 2,592
  3. 2024The Platonic Representation Hypothesiscited by 382
  4. 2025Layer by Layer: Uncovering Hidden Representations in Language Modelscited by 311
  5. 2019On the Measure of Intelligencecited by 144
  6. 2024Exploring the Reasoning Abilities of Multimodal Large Language Models (MLLMs): A Comprehensive Survey on Emerging Trends in Multimodal Reasoningcited by 136
  7. 2024How Large Language Models Encode Context Knowledge? A Layer-Wise Probing Studycited by 64
  8. 2025The Curse of Depth in Large Language Modelscited by 62
  9. 2023Comparing Humans, GPT-4, and GPT-4V On Abstraction and Reasoning Taskscited by 55
  10. 2025The SWE-Bench Illusion: When State-of-the-Art LLMs Remember Instead of Reasoncited by 49
  11. 2024Core Knowledge Deficits in Multi-Modal Language Modelscited by 38
  12. 2024Does Representation Matter? Exploring Intermediate Layers in Large Language Modelscited by 34
9 more
  1. 2024Quantifying Feature Space Universality Across Large Language Models via Sparse Autoencoderscited by 27
  2. 2022Visual representations in the human brain are aligned with large language modelscited by 12
  3. 2025Layers at Similar Depths Generate Similar Activations Across LLM Architecturescited by 12
  4. 2024What Are Large Language Models Mapping to in the Brain? A Case Against Over-Reliance on Brain Scorescited by 10
  5. 2024Can Large Language Models generalize analogy solving like children can?cited by 9
  6. 2024Towards Learning to Reason: Comparing LLMs with Neuro-Symbolic on Arithmetic Relations in Abstract Reasoningcited by 7
  7. 2025Layerwise Recall and the Geometry of Interwoven Knowledge in LLMscited by 6
  8. 2025A large-scale evaluation of commonsense knowledge in humans and large language modelscited by 4
  9. 2025The Representational Alignment between Humans and Language Models is implicitly driven by a Concreteness Effectcited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026Large Language Models Align with the Human Brain during Creative Thinkingcited by 0
  2. 2026Which Attention Heads are like the Human Head? Not the Ones that Computecited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Beyond representational alignment with brain-guided language models for robust reasoning
  2. 2025Large Language Models Are Human-Like Internally
  3. 2026Neural Activation Patterns Across Language Model Architectures: A Comprehensive Analysis of Cognitive Task Performance
  4. 2026Cognitive Expert Language Models Better Align with the Corresponding Brain Systems
  5. 2026Abstraction Induces the Brain Alignment of Language and Speech Models
  6. 2026Abstract representational geometry supports inference in large language models
  7. 2023Divergences between Language Models and Human Brains
  8. 2025Scaling and context steer LLMs along the same computational path as the human brain