Category Ranking
98%
Total Visits
921
Avg Visit Duration
2 minutes
Citations
20
Article Abstract
In the present study, we investigate and compare reasoning in large language models (LLMs) and humans, using a selection of cognitive psychology tools traditionally dedicated to the study of (bounded) rationality. We presented to human participants and an array of pretrained LLMs new variants of classical cognitive experiments, and cross-compared their performances. Our results showed that most of the included models presented reasoning errors akin to those frequently ascribed to error-prone, heuristic-based human reasoning. Notwithstanding this superficial similarity, an in-depth comparison between humans and LLMs indicated important differences with human-like reasoning, with models' limitations disappearing almost entirely in more recent LLMs' releases. Moreover, we show that while it is possible to devise strategies to induce better performance, humans and machines are not equally responsive to the same prompting schemes. We conclude by discussing the epistemological implications and challenges of comparing human and machine behavior for both artificial intelligence and cognitive psychology.
Download full-text PDF |
Source |
|---|---|
| http://www.ncbi.nlm.nih.gov/pmc/articles/PMC11332180 | PMC |
| http://dx.doi.org/10.1038/s44271-024-00091-8 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
The Use of Deep Learning in Primary Agricultural Products Freshness Assessment: A Systematic Review.
J Food Sci
September 2025
College of Food and Bioengineering, Zhengzhou University of Light Industry, Zhengzhou, China.
Primary agricultural products are closely related to our daily lives, as they serve not only as raw materials for food processing but also as products directly purchased by consumers. These products face the issue of freshness decline and spoilage during both production and consumption. Freshness degradation induces sensory deterioration and nutritional loss and promotes harmful substance accumulation, causing gastrointestinal issues or even endangering life.
View Article and Find Full Text PDFTransdiagnostic homogeneity, and diagnostic-specific biomarkers among major depressive disorder, bipolar disorder and schizophrenia during 40 Hz auditory steady-state response: a normative modeling analysis.
J Affect Disord
September 2025
Tianjin University, Medical School, Tianjin, China; Tianjin University, Haihe Laboratory of Brain-Computer Interaction and Human-Machine Integration, Tianjin, China; Tianjin University, State Key Laboratory of Advanced Medical Materials and Medical Devices, Tianjin, China.
Background: Abnormal gamma-band auditory steady-state response (gamma-ASSR) power has been reported in major depressive disorder (MDD), bipolar disorder (BD), and schizophrenia (SZ), but distinguishing between these disorders based solely on power remains challenging. Directed functional connectivity (DFC), which captures topological patterns of causal information flow, may provide more diagnostic-specific markers. However, conventional case-control framework often disregards the substantial individual heterogeneity, yielding unreliable biomarkers.
View Article and Find Full Text PDFScalable Acid-Aided Lysis of Skin Samples Improves Proteome Coverage.
J Invest Dermatol
September 2025
LEO Foundation Skin Immunology Research Center, Department of Immunology and Microbiology, University of Copenhagen, Copenhagen, DK. Electronic address:
Liquid chromatography-mass spectrometry (LC-MS) is an evolving tool for comprehensive proteomic analyses across tissues. Despite the widespread use of LC-MS in dermatology, full-thickness human skin remains challenging to analyse. The skin extracellular matrix (ECM) presents two major obstacles: the extensive crosslinking complicates protein extraction and the high abundance of ECM proteins can mask lower-abundance proteins, reducing identification numbers.
View Article and Find Full Text PDFDominant-negative NARS1 R534* mutation causes wild-type subunit poisoning and heterodimer predominance in cells.
J Biol Chem
September 2025
Department of Integrative Structural and Computational Biology, The Scripps Research Institute, La Jolla, California, USA.
Aminoacyl-tRNA synthetases (aaRSs) catalyze the aminoacylation of tRNA with their cognate amino acids, an essential step in protein biosynthesis. While biallelic mutations in aaRSs often result in severe multi-organ dysfunction accompanied by developmental delays, monoallelic mutations typically cause milder, tissue-specific symptoms. However, a de novo monoallelic nonsense mutation (R534*) in the asparaginyl-tRNA synthetase (AsnRS)-resulting in a premature stop codon and 15-residue C-terminal truncation-has been identified in multiple families and is associated with severe neurodevelopmental symptoms.
View Article and Find Full Text PDFPrediction of intracranial aneurysm rupture from computed tomography angiography using an automated artificial intelligence framework.
Comput Biol Med
September 2025
Department of Neurosurgery, Asan Medical Center, University of Ulsan College of Medicine, Seoul, South Korea.
Intracranial aneurysms (IAs) are common vascular pathologies with a risk of fatal rupture. Human assessment of rupture risk is error prone, and treatment decision for unruptured IAs often rely on expert opinion and institutional policy. Therefore, we aimed to develop a computer-assisted aneurysm rupture prediction framework to help guide the decision-making process and create future decision criteria.
View Article and Find Full Text PDF