arXiv AI September 18, 2026 By Faiz Ghifari Haznitrama, Faeyza Rishad Ardi, Alice Oh

A Neuropsychologically Grounded Evaluation of LLM Cognitive Abilities

The paper introduces NeuroCognition, a benchmark based on three neuropsychological tests—Raven's Progressive Matrices, Spatial Working Memory, and the Wisconsin Card Sorting Test—to evaluate foundational cognitive abilities in large language models (LLMs). It finds that while LLMs excel on text tasks, their performance drops on image-based and more complex tasks, and they fail different parts of the same tasks compared to humans. NeuroCognition correlates with standard general-capability benchmarks yet measures distinct cognitive skills, highlighting where LLMs align with or diverge from human-like intelligence.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv Computation and Language

1d ago

Cognitive Expert Language Models Better Align with the Corresponding Brain Systems

The study investigates whether language models tailored to specific cognitive domains better align with corresponding brain systems. By prompting and fine‑tuning large language models into six domain experts—sensory, spatial, numerical, reasoning, social, and abstract—the authors find that each expert’s representations more closely match the brain region associated with its domain than other experts. This domain‑specific alignment holds across multiple base models and fMRI datasets, while overall prediction accuracy remains largely unchanged, indicating that regional alignment can be obscured when summarizing across the brain.

By Zhivar Sourati, Mengxuan Helen Wu, Nona Ghazizadeh, Jonas Kaplan, Morteza Dehghani, Samuel A. Nastase

llms fine-tuning safety

arXiv AI

Sep 2

Uncovering the Computational Ingredients of Human-Like Representations in LLMs

arXiv:2510.01030v2 Announce Type: replace Abstract: The human ability to translate diverse perceptual and linguistic inputs into structured behavior has been thought to rest on learning robust repres...

By Zach Studdiford, Timothy T. Rogers, Kushin Mukherjee, Siddharth Suresh

llms fine-tuning multimodal benchmarks safety

arXiv AI

Aug 11

In-context superposition: human-like working memory interference in large language models

arXiv:2604. 09670v2 Announce Type: replace-cross Abstract: Intelligent systems must maintain and manipulate task-relevant information online to adapt to dynamic environments and changing goals.

By Hua-Dong Xiong, Li Ji-An, Jiaqi Huang, Robert C. Wilson, Kwonjoon Lee, Xue-Xin Wei

llms

arXiv AI

Aug 14

EgoMonth: A Month-Level Egocentric Video Benchmark for Long-Term Spatiotemporal Memory

arXiv:2608. 13113v1 Announce Type: cross Abstract: Recent advances in Multimodal Large Language Models (MLLMs) have led to substantial progress in video understanding, accompanied by a growing number of long video benchmarks.

By Weitao Chen, Hu Jiaxin, Xie Tianyidan, Yang Li, Yuyi Qian, Banghao Xu, Ziheng Tang, Shenyi Wang, Mingyue Yu, Duo Li, Jiacheng Shi, Gao Wang, Zhan Xu, Zhicheng Qiu, Xuanfu Li, Jian Yang, Lanjun Wang, Zili Yi

llms multimodal benchmarks

arXiv AI

Jul 28

Spatial-IQ: Deconstructing Spatial Intelligence via Hierarchical Capability Tests

arXiv:2607. 22864v1 Announce Type: cross Abstract: Multimodal large language models (MLLMs) excel at visual interpretation but fail on spatial reasoning tasks that humans solve reliably.

By Patrick Rim, Tom Long, Ekta Prashnani, Ruth Rosenholtz, Ben Boudaoud, Peter Xenopoulos, Alex Wong, Joohwan Kim, Jae-Hyun Jung

llms reinforcement-learning multimodal benchmarks

arXiv AI

Aug 7

Small Foundation Models of Human Cognition and Behaviour

arXiv:2608. 05224v1 Announce Type: new Abstract: Large language models fine-tuned on human behavioural data have emerged as general-purpose cognitive proxies, but the scale this requires, and whether these models process task structure or exploit statistical shortcuts, remain open questions.

By Nick Oh, Fernand Gobet

llms fine-tuning

One email a morning, machine-written

Related stories

Cognitive Expert Language Models Better Align with the Corresponding Brain Systems

Uncovering the Computational Ingredients of Human-Like Representations in LLMs

In-context superposition: human-like working memory interference in large language models

EgoMonth: A Month-Level Egocentric Video Benchmark for Long-Term Spatiotemporal Memory

Spatial-IQ: Deconstructing Spatial Intelligence via Hierarchical Capability Tests

Small Foundation Models of Human Cognition and Behaviour