SPAGYRIC HERBALISM

Mediterranean rockrose extract shows fungicidal activity against fungi that cause common skin infections

A polyphenol-rich extract from Cistus salviifolius showed fungicidal activity against several dermatophytes and reduced fungal infection in a reconstructed human epidermis model

Universidad Miguel Hernandez de Elche

Facebook

XLinkedInWeChat
WhatsAppEmail

image: 

Transmission electron microscopy images of the dermatophytes T. rubrum (A–F) and M. canis (G–L). The images show untreated cells (A, B, G, H) and cells treated with C. salviifolius extract (C–F, I–L), showing alterations in cellular structure. Arrows indicate autophagy-like structures. Source: Álvarez-Martínez et al., Journal of Ethnopharmacology.

view more 

Credit: Álvarez-Martínez et al., Journal of Ethnopharmacology. / UMH

A polyphenol-rich extract from Cistus salviifolius, a Mediterranean rockrose species traditionally used to treat skin conditions, has shown fungicidal activity against several dermatophytes, the fungi responsible for superficial infections of the skin, hair and nails. The study, conducted by researchers from Miguel Hernández University of Elche (UMH), together with the universities of Namur (Belgium) and Coimbra (Portugal), has been published in Journal of Ethnopharmacology.

Dermatophytes are fungi capable of colonizing keratin-rich tissues such as the skin, hair and nails, causing very common infections, including different types of ringworm. The researchers prepared the polyphenol-rich extract from plants grown in the controlled gardens at UMH and tested its activity against different fungal species. Dermatophytes were particularly sensitive, especially Trichophyton rubrum—one of the main causes of fungal skin infections—and Microsporum canis, which can be transmitted from animals to humans. In contrast, the extract showed no antifungal activity at the concentrations tested against yeasts such as Candida albicans.

From traditional use to laboratory testing

The rockrose species studied is a resilient, sun-loving evergreen shrub native to the Mediterranean Basin that thrives in dry, rocky soils. It has traditionally been used in different regions in topical preparations to treat wounds, inflammation and skin infections. “Traditional medicine provides us with clues, but we need to experimentally determine what lies behind these uses, what biological processes are actually taking place and under what conditions they may be useful,” explains Vicente Micol Molina, a researcher at the Institute for Research in Biotechnology and Health (IDiBE) at UMH. The results do not support applying the plant directly to the skin, but rather support further research into controlled formulations in which the composition and behavior of the extract are known.

Before testing its effect against fungi, the team had already analyzed the composition of the extract using techniques capable of separating and identifying its molecules. They found that it was composed mainly of polyphenols, including tannins and flavonoids. To investigate how the extract acted, they examined treated fungi using electron microscopy. The images revealed major alterations: large vacuoles, disorganization of the cell interior, membrane detachment and cellular debris outside the cells, suggesting that some cells had lost their contents or ruptured. The authors suggest that the extract may disrupt several fungal cellular processes at once, although further research is needed to determine which compounds are responsible for its activity.

“We observed that the fungus stops growing and that its cells sustain substantial damage. This helps us understand why the rockrose extract has fungicidal activity and allows us to begin investigating the specific mechanisms involved,” says Francisco Javier Álvarez Martínez, IDiBE researcher and first author of the study.

Testing the extract in a human epidermis model

The extract was also tested on reconstructed human epidermis, tissue grown in the laboratory from primary keratinocytes, the cells that make up most of the outer layer of the skin.The researchers infected this tissue with dermatophytes to study whether the treatment could slow the infection and protect the skin barrier. When applied after infection, the rockrose extract reduced fungal load and tissue invasion, preserved the epidermal barrier and decreased the inflammatory response. It also did not reduce keratinocyte viability under the conditions tested.

“This means that, in this model and at the concentrations used, the extract showed no toxicity to the main cells of the epidermis. This is an important result, although it is still not enough to say that it is safe as a treatment in humans,” the UMH researcher cautions.

Potential for future topical formulations

The study also detected antioxidant activity and the ability to inhibit enzymes that degrade skin components such as collagen, elastin and hyaluronic acid. These results support further investigation of Cistus salviifolius extract for the development of potential topical formulations, such as creams or hydrogels, but it has not yet been tested as a treatment in humans. The next steps include studying its effects on resistant fungal strains, developing formulations, and confirming its safety and efficacy in animal models and, subsequently, in clinical trials.

In addition to Álvarez Martínez and Micol Molina, the UMH researchers involved in the study include IDiBE researcher Nerea Pons Rocamora and IDiBE researcher Enrique Barrajón Catalán, together with researchers from the universities of Namur and Coimbra. The research received European funding and support from public bodies in Spain, Portugal and Belgium, including the European Union through the NextGenerationEU programme, as well as the Generalitat Valenciana, the Valencian Innovation Agency and the Daniel and Nina Carasso Foundation.

---

Journal

Journal of Ethnopharmacology

DOI

10.1016/j.jep.2026.122196

Method of Research

Experimental study

Subject of Research

Lab-produced tissue samples

Article Title

Polyphenol-rich Cistus salviifolius L. extract exerts fungicidal activity against dermatophytes through severe ultrastructural disruption

Cistus salviifolius, Cistaceae -

Credit

Jeantosti. Wikimedia Commons. https://commons.wikimedia.org/wiki/File:Ciste2.jpg

 

Historic fishery collapse holds lessons for the present

The study is based on a unique dataset: a 450-year time series of herring catches in the Sound from 1200 to 1650.

A combination of climate change, overfishing, and social change caused the herring of the Sound to disappear.

German Centre for Integrative Biodiversity Research Halle-Jena-Leipzig – iDiv e. V.

Facebook

XLinkedInWeChatBlueskyMessageWhatsAppEmail

image: 

The study shows herring stock itself did shrink markedly in the 16th century, but it did not collapse completely. It was only the combined effect of several factors – environmental change, overfishing, and social change – that brought the profitable fishery to a sudden end.

view more 

Credit: The University of Kiel / Schwermer

From the 13th to the 16th century, herring from the Sound – the strait in the Baltic Sea between Denmark and Sweden – was one of northern Europe’s most important trade goods. Salted herring from the so-called Skanör-Falsterbo fishery fed large parts of Europe. Around 1570, however, this fishery collapsed within a short period of time – with far-reaching consequences for trade, politics, and society. It took almost 400 years, until the 1950s, before comparable catch volumes were reached again. An international team of fisheries economists, ecologists, and historians led by Kiel University (CAU) and the German Centre for Integrative Biodiversity Research (iDiv) has now investigated why this fishery, stable for centuries, collapsed so suddenly. The results show that the collapse of the fishery cannot be explained by a simple stock collapse alone. The herring stock itself did shrink markedly in the 16th century, but it did not collapse completely. It was only the combined effect of several factors – environmental change, overfishing and social change – that brought the profitable fishery to a sudden end. The new study was published in Nature Sustainability.

“Only when you look at climate, ecology and socio-economic conditions together does a coherent picture of this historic collapse emerge", says first author Dr Rudi Voss, fisheries economist at iDiv and CAU. “None of these factors alone would have brought the fishery down. It is their interplay that explains the dynamics.”

An extraordinary time series: 450 years of fishery history

The study is based on a unique dataset: a 450-year time series of herring catches in the Sound from 1200 to 1650. It was reconstructed using fragmentary historical sources, including customs records, royal pre-emption rights (“kongekøb”), and other archival material documenting trade volumes for individual years and locations. Gaps in the data were filled using economic and ecological indicators such as the availability of salt – the most important production factor for the herring industry at the time – and reconstructed climate data. This gives the researchers a fishery dataset that extends far beyond the usual modern stock time series, which typically span only a few decades. It allowed them to study how climate change, economic crises, and overexploitation played out over decades and centuries, and to determine how these factors reinforced one another.

Interplay rather than a single cause

To reconstruct the dynamics of the fishery, the team combined two methodological approaches: a newly developed bio-economic stock assessment method (BESA), which uses historical catch and price data to estimate both sustainable catch levels and the state of the herring stock over time. In addition they used a so-called loop analysis – a method from ecology that can map complex interactions between ecological, economic and social factors within a single model, without requiring every variable to be precisely quantified. In detail: overfishing had already weakened the stock and increased fishing costs. At the same time, the onset of the “Little Ice Age” brought a period of cooling to the Baltic region, which affected the stock’s productivity and reduced it further. In parallel, social and economic conditions deteriorated: shifting dunes destroyed the infrastructure of the fishing sites, a newly imposed system of serfdom tying peasants to the land deprived the fishery of workers, and cheaper herring from the rising North Sea fishery pushed Baltic herring out of the market.

A lesson for fisheries management today

Herring in the western Baltic Sea currently lies outside safe biological limits and on the brink of collapse; a zero-catch recommendation is already in place for it. According to the authors, an interdisciplinary approach – closely combining fisheries economics, climate research, ecology, and economic history – yields more than new historical insights: these findings can also be applied directly to today’s fisheries policy. Anyone who assesses the current state of a fishery on the basis of biological stock data alone may overlook crucial risk factors. Although the focus today is on a different biological stock, what both cases share is that environmental conditions in addition to fishing pressure are hindering their recovery. Whereas a period of cooling during the “Little Ice Age” affected the stock in the past, today the warming of the Baltic Sea caused by climate change represents an additional stressor.

The study therefore supports the approach of Ecosystem-Based Fisheries Management, which takes ecological and socio-economic factors into account together – for example infrastructure, economic diversification and the social situation of fishing communities. “Looking back at history makes it clear: sustainable fisheries only succeed if we take social and economic conditions just as seriously as the state of the stock itself. That is the lesson from 450 years of herring fishing in the Sound – and it is just as relevant today as it was then,” concludes first author Voss.

Credit

The University of Kiel / Schwerme

Journal

Nature Sustainability

DOI

10.1038/s41893-026-01937-1

Method of Research

Observational study

Subject of Research

Animals

Article Title

Historic fishery collapse holds lessons for the present

Article Publication Date

28-Sep-2026

 

Waves find order in the chaos of an oddly shaped cavity

CUNY ASRC researchers discover stable, repeating wave patterns in a metamaterial system, opening new possibilities for controlling light and sound

Advanced Science Research Center, GC/CUNY

Facebook

XLinkedInWeChat

image: 

Artistic rendering of a hyperbolic wave attractor forming in an odd-shaped cavity inside a hyperbolic material.

view more 

Credit: Andrea Alu

NEW YORK, September 28, 2026 — When light or sound bounces around inside an oddly shaped room, its reflections can quickly become difficult to predict. But new research led by scientists at the Advanced Science Research Center at the CUNY Graduate Center (CUNY ASRC) shows that waves can behave very differently when they travel through a special class of materials.

The study, published in Nature Physics, demonstrates that waves inside an irregularly shaped cavity made from hyperbolic materials (which are named after the hyperbola mathematical curve because of the unique shape these materials force light waves to take) can organize into stable, repeating paths rather than scattering chaotically. The researchers call these structures “hyperbolic wave attractors,” and their findings could eventually help scientists and engineers design new ways to control light, radio waves, and sound in complex environments.

“This work shows how geometry and the properties of a material can work together to produce wave behavior that is both surprising and useful,” said Andrea Alù, the study’s principal investigator, director of the Photonics Initiative at the CUNY ASRC, and Distinguished Professor of Physics at the CUNY Graduate Center. “By understanding how waves organize themselves in these hyperbolic media, we can begin to explore new approaches to controlling energy, information, and communication signals in complex environments.”

When waves take an unusual turn

In everyday materials, waves generally reflect from a surface in a familiar way: The angle at which a wave arrives matches the angle at which it leaves. In an irregularly shaped room, repeated reflections can send waves in many directions, creating complex chaotic patterns. This is the basis of a classic physics problem known as a dynamical billiard, in which the motion of a ball — or, in the wave version, light — inside a curved or irregular container quickly becomes unpredictable.

Hyperbolic materials can drastically change this picture. These materials have unusual properties that force waves to travel along narrow, highly defined directions instead of spreading freely in all directions. As a result, when a wave encounters a tilted wall, its outgoing direction can differ from what would be expected in an ordinary material.

Alù’s team wanted to understand what would happen when these unusual reflection rules were combined with an irregularly shaped cavity.

“Normally, we expect a complicated cavity to produce complicated, chaotic wave patterns,” said Simon Yves, a postdoctoral researcher in Alù’s lab and a first author of the study. “Here, the opposite happens. The unusual propagation and reflection of waves create a strong geometric organization, producing well-defined paths that can persist across a broad range of wavelengths.”

From chaos to wave attractors

The researchers found that the waves inside their cavity can progressively organize into closed trajectories. These paths are stable and scale-invariant, meaning their underlying geometric structure persists across different scales.

The effect arises from a breaking of mirror symmetry in the wave-reflection process. As waves bounce around the cavity, their wavelengths progressively shrink, helping create the conditions for the formation of the attractors.

The resulting wave patterns also have a property called handedness. This describes whether the defined wave’s trajectory inside the cavity rotates clockwise or counterclockwise. The attractors’ handedness and stability are connected to the unusual geometry of wave propagation in the hyperbolic material.

The team demonstrated these effects by engineering vibrations in a mechanical metamaterial, a human-made structure designed to control how waves move through it.

“The most exciting aspect of these results is that they connect a simple geometric idea with a rich set of wave phenomena,” said Enrico Renzi, a doctoral student in Alù’s lab and a first author of the study. “We can observe how the waves become organized, and we can connect that organization to properties such as stability and handedness. This gives us a framework for designing wave behavior rather than simply observing it.”

A bridge from ocean waves to nanophotonics

The researchers’ findings have intriguing parallels with internal wave attractors studied in oceanography and fluid dynamics. In oceans and other stratified fluids, waves traveling through water with density gradients can reflect unusually from underwater slopes. These reflections can focus energy into closed paths and contribute to wave turbulence.

The new study translates a related phenomenon into a tabletop, solid-state metamaterial platform, showing how concepts from geophysical fluid dynamics can be explored in engineered materials and in simple linear settings.

The framework that the scientists introduced can also extend to hyperbolic phonon polaritons — hybrid light-matter excitations that can arise in natural two-dimensional anisotropic crystals such as hexagonal boron nitride and molybdenum trioxide, which support similarly odd propagation and reflection properties. These materials can support light confined to tiny regions, offering opportunities for low-loss nanophotonic circuits, enhanced interactions between light and matter, and control of infrared light.

In the future, hyperbolic wave attractors could inform the design of compact optical chips, devices that separate optical signals, particle-trapping systems, analog wave-computing platforms, and highly sensitive biological sensors.

“This research opens a path toward engineering stable and robust wave patterns in systems where waves would normally be expected to rapidly become chaotic,” Alù said. “Our goal is to understand how these effects can be harnessed to create new functionalities for photonics, phononics, and wave-based technologies.”

The research was supported by the Simons Foundation and the National Science Foundation Science and Technology Center “New Frontiers of Sound.” The research team included scientists affiliated with the CUNY ASRC and Institut Langevin at ESPCI Paris PSL in France, as well as the University of Amsterdam in the Netherlands.

About the Advanced Science Research Center at the CUNY Graduate Center

The Advanced Science Research Center at the CUNY Graduate Center (CUNY ASRC) is a world-leading center of scientific excellence that elevates STEM inquiry and education at CUNY and beyond. The CUNY ASRC’s research initiatives span five distinctive, but broadly interconnected disciplines: nanoscience, photonics, neuroscience, structural biology, and environmental sciences. The center promotes a collaborative, interdisciplinary research culture where renowned and emerging scientists advance their discoveries using state-of-the-art equipment and cutting-edge core facilities.

About the Graduate Center of The City University of New York
The CUNY Graduate Center is a leader in public graduate education devoted to enhancing the public good through pioneering research, serious learning, and reasoned debate. The Graduate Center offers ambitious students over 50 doctoral, master’s, and certificate programs of the highest caliber, taught by top faculty from throughout CUNY — the nation’s largest urban public university. Through its nearly 40 centers, institutes, initiatives, and the Advanced Science Research Center, the Graduate Center influences public policy and discourse and shapes innovation. The Graduate Center’s extensive public programs make it a home for culture and conversation. 

---

Journal

Nature Physics

DOI

10.1038/s41567-026-03453-7

Method of Research

Experimental study

Article Title

Hyperbolic wave attractors

Article Publication Date

28-Sep-2026

 

Foods with shorter shelf life are seen as more natural and healthier: UBC study

University of British Columbia

Facebook

XLinkedInWeChatBlueskyMessageWhatsAppEmail

For years nutrition experts have warned about the many risks of eating ultra-processed foods: among them obesity, cardiovascular disease and diabetes. Instead, they advise that consumers opt for more natural offerings.  

So how, then, are shoppers determining the naturalness of a food? According to a fascinating new study from the UBC Sauder School of Business, they’re using product shelf lives as a shorthand, even when they aren’t a reliable indicator. 

For the study, titled Naturalness against environment-friendliness: The impact of shelf life on food perceptions and purchase decisions, researchers performed a series of experiments. In one, participants compared potato chips that had five-month and nine-month shelf lives, and rated the five-month chips as more natural and healthier, while those with the longer shelf life were considered more environmentally friendly and better for reducing waste.  

In another, participants chose between pasta sauces that had one- and three-year shelf lives. When the researchers emphasized the importance of consuming natural foods, nearly 70 per cent chose the item with the one-year shelf life; when they emphasized the importance of protecting the environment, that number plummeted to 43 per cent. 

Amazingly, even when participants were shown the only reason behind a product’s longer shelf life was better packaging (a high-performance seal on a mayonnaise jar), when naturalness mattered, they still opted for the mayo with a shorter life. Likewise, even when participants were shown two granola bars with nearly identical ingredients and nutritional information but different shelf lives, when naturalness mattered, they still opted for the granola with a shorter life. 

The researchers believe consumers are using shelf life as a kind of mental shortcut to determine naturalness, and in the process may choose foods that are more likely to be wasted.   

“We provide all the necessary information to make a rational choice. We provide ingredient lists. We provide nutritional facts. But it's a lot to process,” explains UBC Sauder Associate Professor Dr. Yann Cornil, who co-authored the study with Dr. Dan Liu of Jinan University and Dr. Xiaobing Xu of Hainan University. Like shoppers in a supermarket, he says, study participants instead tend to rely on “peripheral cues,” including shelf life, packaging and marketing, to reach conclusions about whether a product is natural or not. 

The study is especially timely, given that roughly 46 per cent of Canadians’ daily caloric intake is from ultra-processed foods. In the U.S. that number is even higher, at roughly 55 per cent. Often made from substances extracted from sugars, oils and starches, the foods are dramatically altered from their natural state and can be high in sodium, saturated fat, or added sugar, and lower in nutrients. 

Dr. Cornil says there’s been a shift in nutrition science, from concern over foods that are high in fat and sugar to ones that are highly processed. Now, when consumers think of a food as natural, they will generally consider it healthy, and they see foods with longer shelf life as less natural. 

“To some extent they are correct, because the more you extend the shelf life of a food, the more likely it went through this ultra-processing technique… but not necessarily,” says Dr. Cornil. Packaging has improved dramatically, he explains, and better packaging has improved conservation, just like refrigeration did 60 years ago.  

Still, consumers overestimate the relationship between shelf life and naturalness, and that can lead to unnecessary food waste.  

“By looking for natural foods, consumers tend to prefer foods with a shorter shelf life, even though foods with a longer shelf life could be just as good, and just as healthy and natural, as we show in the paper,” says Dr. Cornil. “So by trying to choose natural foods, they might run the risk of choosing foods they will eventually waste because they have too little time to consume them.” 

Dr. Cornil says consumers regularly misunderstand shelf life, and toss foods that are still fine to eat. As a result, some manufacturers are even indicating on their packaging that foods can still be safely consumed after their best before dates, although he notes that less scrupulous manufacturers might take advantage of the fact that consumers have to repurchase their products more often. Improvements to packaging are also reducing waste, but as the paper shows, consumers aren’t always sold on the idea. 

The study is the first of its kind to demonstrate the tension between environmental friendliness and naturalness, as well as the power of the shelf-life heuristic, that is, the mental shortcut consumers use to determine naturalness. 

“The fact that we still find this effect even when we provide nutrition information, and even when we make consumers understand that packaging is responsible for the longer shelf life and not processing, is really interesting,” says Dr. Cornil. “And we go pretty far in showing the strength of this misleading heuristic.” 

---

Journal

Journal of Consumer Psychology

DOI

10.1002/jcpy.70034

Article Title

Naturalness against environment-friendliness: The impact of shelf life on food perceptions and purchase decisions

 

AI chatbots give us a narrow slice of knowledge: Researchers warn of ‘knowledge collapse’

University of Copenhagen

LinkedInWeChatBlueskyMessageWhatsAppEmail

“Let me just ask the chatbot.” For many of us, this has become an everyday phrase. Where we used to turn to Google to find information, AI chatbots have become a common way of getting answers to everything from what to make for dinner and how to word that difficult email to the boss, to what it actually means when interest rates rise.

But the large language models underpinning AI chatbots give us a significantly narrower range of information than a conventional web search. This is the finding of a new study led by researchers at the Department of Computer Science (DIKU) at the University of Copenhagen.

“Every language model we tested provides users with more uniform information than a simple Google search across all the topics we looked at. In other words, people are to a large extent exposed to the same information over and over again. So AI chatbots are not just changing how we find knowledge, but also which knowledge we have access to,” says first author Dustin Wright, a former postdoctoral researcher at DIKU who is now an assistant professor at Aalborg University.

At least 18% less diverse than Google

The researchers tested 27 different large language models on 155 topics. For each topic, they used 200 different prompt formulations based on questions from real users. This generated a dataset containing around 70 million individual claims produced by the models.

The results show that even the language model producing the most diverse answers – OpenAI’s GPT-5 – provides at least 18.7 per cent less varied information than Google. The topics tested by the researchers ranged from nuclear weapons, marriage, pornography, racism and genocide to more country-specific topics such as Marine Le Pen, the Falklands War and K-pop.

According to the researchers, the fact that people are increasingly using AI models as their primary gateway to information could have significant consequences:

“We risk exposing people to fewer perspectives and a narrower range of knowledge. This could create a vicious cycle in which the most popular content becomes even more dominant, while other content is increasingly overlooked,” says Professor at DIKU and senior author Isabelle Augenstein, adding:

“It’s similar to globalisation. Today, you can buy the same products and find the same coffee chains almost everywhere in the world. That has many advantages, but it has also reduced diversity.”

Why is diversity so low?

According to the researchers, the low level of diversity in language models is partly a result of how the models basically work. They compress the vast amount of text they are trained on and learn the patterns that occur most frequently. In the process, information that deviates from the most common patterns is filtered out.

The effect could be amplified if language models are increasingly trained on text produced by other AI models – something the researchers expect to happen. In that case, models would learn from their own outputs, which are already less diverse than the human-written texts on which they were originally trained.

If this process is repeated over several generations of models, the range of information could gradually become narrower. This is what the researchers refer to as ‘knowledge collapse’.

“It’s a worrying thought. However, we can see that the more recent models produce slightly more diverse answers than older models, so knowledge collapse is not happening yet. But the mechanism that could trigger it in the longer term is already there. So it is something we should be aware of,” says Isabelle Augenstein.

Seek out different sources

The researchers therefore also hope that people will use AI thoughtfully:

“AI chatbot summaries can of course be useful – that is why so many people use them. But it is still important to seek out different sources in order to understand the nuances and get a broader picture – especially for the younger generation growing up with AI. We must not become so dependent on the technology that we stop understanding and thinking for ourselves,” says Isabelle Augenstein.

The AI industry should also pay attention to the issue, the researchers argue:

“We hope AI developers will build language models in a way that preserves the breadth of knowledge available to us. We have developed a method that they can use to measure diversity in models, which could help ensure that future language models do not become less diverse,” says Dustin Wright.

 

[FACT BOX] ABOUT THE STUDY

• The researchers analysed 27 large language models from OpenAI, Meta, Google and Alibaba.
• The models were tested on 155 topics relating to 12 different countries.
• The analysis covered around 1.7 million AI-generated answers and approximately 70 million individual claims.
• The results show, among other things, that smaller AI models generate more diverse content than larger models, and that newer models are more diverse than older models. Overall, however, all the models had significantly lower diversity than traditional web search engines.
• The research was conducted by researchers from the University of Copenhagen, Aalborg University, Stanford University, the University of Colorado Boulder and the University of Texas at Austin.
• The study has been accepted for the international research conference EMNLP 2026, which takes place in October 2026. Read the research paper on arXiv.

 

[FACT BOX] HOW DOES AN AI CHATBOT WORK?

An AI chatbot is a service such as ChatGPT, Gemini or Claude that you can communicate with by typing or speaking and that provides answers in return. The chatbot uses a so-called large language model to understand questions and formulate responses.

A large language model is the underlying AI model that powers the chatbot. It is trained on very large amounts of text and learns patterns in how words and sentences relate to one another.

When you type a question into an AI chatbot, the chatbot sends it to the underlying large language model, which generates a response by predicting which words are most likely to fit your question.

---

DOI

10.48550/arXiv.2510.04226

Article Title

What and Whose Knowledge? Measuring Epistemic Diversity in Large Language Models