(Press-News.org) When large language models (LLMs) make decisions about networking and friendship, the models tend to act like people, across both synthetic simulations and real-world network contexts. Marios Papachristou and Yuan Yuan developed a framework to study network formation behaviors of multiple LLM agents and compared these behaviors against human behaviors. The authors conducted simulations using several large language models placed in a network, which were asked to choose which other nodes to connect with, given their number of connections, common neighbors, and shared attributes, like arbitrarily assigned “hobbies” or “location.” The authors varied the network context, including simulations of friendships and workplace, communities; the amount of information provided to the agents; and model parameters like temperature. Generally, LLMs exhibited tendencies to connect to other nodes that were already well connected, a phenomenon called “preferential attachment.” LLLs also showed a tendency to connect to other nodes with a high number of common connections, a phenomenon called “triadic closure.” LLMs also demonstrated homophily, choosing nodes with similar hobbies or location, as well as the “small-world” phenomenon, where any two nodes are connected by surprisingly short chains of acquaintances often with just a few “degrees of separation.” In network simulations based on real Facebook friendship networks, work networks, and telecommunication networks, LLM models prioritized homophily most strongly, followed by triadic closure and preferential attachment. Finally, the authors conducted a controlled survey with around 100 human participants and asked participants and to respond to the same survey. LLMs' responses showed strong alignment with human link-formation choices, though the models displayed higher internal consistency than humans. According to the authors, these findings demonstrate the potential for LLMs to be used as a source of synthetic data when privacy concerns preclude using human data, but also raise questions regarding the design and alignment of artificial intelligence systems that make real-world decisions by interacting with human networks.
END
LLMs choose friends and colleagues like people
2025-12-02
ELSE PRESS RELEASES FROM THIS DATE:
Gas stoves and nitrogen dioxide exposure
2025-12-02
Twenty-two million Americans would no longer be breathing in unhealthy levels of nitrogen dioxide if they switched from gas and propane stoves to electric stoves. Robert Jackson and colleagues combined outdoor air quality data with estimates of indoor nitrogen dioxide emissions from stoves in more than fifteen cities. As outdoor air quality improves, stoves become an increasingly important source of exposure. According to the World Health Organization, health risks to the respiratory system increase at levels above ...
Beauty linked with metabolic costs of perceiving images
2025-12-02
Humans may find images that take less energy to process aesthetically pleasing, suggesting that our attraction to beauty is at least partially an energy conservation strategy.
Looking at something can feel effortless, but in energetic terms, it isn’t cheap. The brain uses 20% of the body’s energy, and the visual system accounts for about 44% of that expenditure. Looking at very simple stimuli, like a blank white room, is energy-efficient but boring. Looking at very busy or unusual image can feel tiring and unpleasant. Yikai Tang and colleagues presented 4,914 ...
First Nations Australians twice as likely to be digitally excluded: report
2025-12-02
First Nations Australians are twice as likely as other Australians to be digitally excluded and face barriers to accessing, affording and using the internet. For those living in remote Australia, the barriers are much greater.
Three in four First Nations people living in remote and very remote communities are digitally excluded according to the Mapping the Digital Gap report by RMIT University and Swinburne University of Technology. This means many face significant barriers to accessing and using online services needed for daily social, economic and cultural life.
This 2025 outcomes report draws on three years of ...
Korea University study finds restless legs syndrome linked to Parkinson’s risk—dopamine treatment may be protective
2025-12-02
Restless legs syndrome (RLS) is a common neurological sleep disorder characterized by an uncontrollable urge to move the legs, often worsening at night. Parkinson’s disease (PD), a progressive neurodegenerative disorder, is marked by tremor, rigidity, and slowed movement. Both conditions are associated with dysfunction in the brain’s dopaminergic system, but their causal relationship has remained unclear.
A joint research team from Korea University Ansan Hospital, Pohang Stroke and Spine Hospital, and National Health ...
Pusan National University researchers use AI to create optimized engine components that outperform human designs
2025-12-02
Gerotor pumps for oil circulation and lubrication are crucial components in automotive and hydraulic systems. They possess a compact design, excellent flow rate per rotation, and high suction capability. The gerotor tooth profile plays a significant role in determining the overall performance of hydraulic systems for engine lubrication and automatic transmission. Unfortunately, conventional design methods leverage predefined mathematical curves and iterative adjustments, which compromises their optimization ...
Approximate domain unlearning: Enabling safer and more controllable vision-language models
2025-12-02
Vision-language model (VLM) is a core technology of modern artificial intelligence (AI), and it can be used to represent different forms of expression or learning, such as photographs, illustrations, and sketches. It has high generalization ability, which allows it to accurately recognize objects in images within a domain. However, this generalization ability is at risk. For example, VLM recognizes both real cars and illustrated cars as “cars.” If this is installed in a system, there is a risk that a car illustrated in a roadside advertisement ...
Moths detect bat attack signals: Ultrasonic pulse rates drive distinct escape responses
2025-12-02
For many nocturnal moths, hearing sound waves is a matter of survival in night sky. Their ability to detect ultrasonic calls emitted by bats determines whether they escape or become prey. This predator-prey relationship has shaped the behavior, physiology, and sensory systems of both groups. Echolocating bats have developed complex call patterns to track insects in flight, while moths have evolved remarkable countermeasures, including evasive flight and sound-deflection tactics. The luna moth, for instance, spins its long hindwings to deflect the ultrasonic ...
Intimate partner violence injury patterns linked with suicidal behavior
2025-12-02
CHICAGO – Victims of intimate partner violence with suicidal behavior have characteristic injury patterns on medical imaging, according to a new study being presented today at the annual meeting of the Radiological Society of North America (RSNA). The findings open the door to improved screening and earlier intervention to better protect these vulnerable populations, the researchers said.
Intimate partner violence is the physical, emotional or sexual abuse of a person by their partner or spouse. It is an increasingly recognized risk factor for suicidal behavior, and victims of intimate partner violence ...
Blood test shows obesity speeds Alzheimer’s development
2025-12-02
CHICAGO – Researchers have conducted the first study evaluating the impact of obesity on Alzheimer’s disease blood biomarkers (BBMs). BBM values increased up to 95% faster in individuals with obesity than in non-obese individuals, according to a new study being presented today at the annual meeting of the Radiological Society of North America (RSNA).
“This is the first time we’ve shown the relationship between obesity and Alzheimer’s disease as measured by blood biomarker tests,” said Cyrus ...
New study supports the value of medical humanities in illuminating the root causes of health care disparities in Washington, DC
2025-12-02
WASHINGTON -- A new study analyzing dozens of published papers over five decades focusing on health care disparities in Washington, DC, found that those that employed medical humanities approaches identified crucial barriers and opportunities for intervention that quantitative studies often miss.
Lead author Sweta Ghatti, a fourth year student at Georgetown School of Medicine, began the study as part of a Mitchell Summer Research Scholarship project addressing health challenges in the District. Ghatti worked closely with senior author Lakshmi Krishnan, MD, PhD, assistant professor ...