Category Ranking

98%

Total Visits

921

Avg Visit Duration

2 minutes

Citations

20

Article Abstract

Large Language Models (LLMs) have shown remarkable promise in communicating with humans. Their potential use as artificial partners with humans in sociological experiments involving conversation is an exciting prospect. But how viable is it? Here, we rigorously test the limits of agents that debate using LLMs in a preregistered study that runs multiple debate-based opinion consensus games. Each game starts with six humans, six agents, or three humans and three agents. We found that agents can blend in and concentrate on a debate's topic better than humans, improving the productivity of all players. Yet, humans perceive agents as less convincing and confident than other humans, and several behavioral metrics of humans and agents we collected deviate measurably from each other. We observed that agents are already decent debaters, but their behavior generates a pattern distinctly different from the human-generated data.

Download full-text PDF

Source
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC12015287PMC
http://dx.doi.org/10.1038/s41598-025-98378-1DOI Listing

Publication Analysis

Top Keywords

humans
9
large language
8
language models
8
humans agents
8
agents
7
testing limits
4
limits large
4
models debating
4
debating humans
4
humans large
4

Similar Publications

An aptasensor-based fluorescent signal amplification strategy for highly sensitive detection of mycotoxins.

Anal Methods

September 2025

Key Laboratory of Biorheological Science and Technology of Ministry of Education, College of Bioengineering, Chongqing University, Chongqing 400044, P. R. China.

Aflatoxin B1 (AFB1) is one of the most toxic mycotoxins that pose great health threats to humans. Herein, an aptasensor-based fluorescent signal amplification strategy is developed for the detection of AFB1. Initially, the AFB1 aptamers labelled with carboxyfluorescein (FAM) are adsorbed onto graphene oxide (GO), triggering energy transfer.

View Article and Find Full Text PDF

Systematic analyses uncover plasma proteins linked to incident cardiovascular diseases.

Protein Cell

August 2025

Department of Neurology and National Center for Neurological Disorders, Huashan Hospital, State Key Laboratory of Medical Neurobiology and MOE Frontiers Center for Brain Science, Fudan University, Shanghai 200433, China.

Cardiovascular disease (CVD) research is hindered by limited comprehensive analyses of plasma proteome across disease subtypes. Here, we systematically investigated the associations between plasma proteins and cardiovascular outcomes in 53,026 UK Biobank participants over a 14-year follow-up. Association analyses identified 3,089 significant associations involving 892 unique protein analytes across 13 CVD outcomes.

View Article and Find Full Text PDF

Objective: This study investigated the locations of amino acid modifications within two major human hair keratins (Type I K31 and Type II K85) with probable implications for protein and hair structural component integrity. The particular focus was on cysteine modifications that disrupt intra-protein and inter-protein disulphide bonds.

Methods: Human hair was exposed to accelerated, sequential heat or UV treatments, simulating effects resulting from the use of heated styling tools and environmental exposure over a time frame approximating one year.

View Article and Find Full Text PDF

Ultrasonographic Analysis of Site-Specific Plantar Skin Thickness for Melanoma Staging and Excision.

Clin Anat

September 2025

Division in Anatomy and Developmental Biology, Department of Oral Biology, Human Identification Research Institute, BK21 FOUR Project, Yonsei University College of Dentistry, Seoul, South Korea.

Plantar melanomas present unique diagnostic and surgical challenges owing to substantial regional variations in skin thickness. Although the Breslow thickness remains the primary criterion for staging and surgical excision, its application on plantar melanoma is complicated by the inherent thickness of the glabrous plantar epidermis, which may lead to tumor depth overestimation. Accurate assessment of plantar skin thickness is essential for optimizing staging accuracy and refining surgical margins.

View Article and Find Full Text PDF

Introduction: We compared and measured alignment between the Health Level Seven (HL7) Fast Healthcare Interoperability Resources (FHIR) standard used by electronic health records (EHRs), the Clinical Data Interchange Standards Consortium (CDISC) standards used by industry, and the Uniform Data Set (UDS) used by the Alzheimer's Disease Research Centers (ADRCs).

Methods: The ADRC UDS, consisting of 5959 data elements across eleven packets, was mapped to FHIR and CDISC standards by two independent mappers, with discrepancies adjudicated by experts.

Results: Forty-five percent of the 5959 UDS data elements mapped to the FHIR standard, indicating possible electronic obtainment from EHRs.

View Article and Find Full Text PDF