LLMs change judgments when told who wrote a text (English, Level A1)

Researchers work at the University of Zurich.
They study large language models (LLMs).
Each model makes fifty narrative statements.
The statements cover 24 controversial topics.
When no source is given, models agree over 90%.
When an author is named, models change their answers.
All models showed a strong anti-Chinese bias.
Models trust human authors more than other AIs.
Researchers say we need transparency and governance.

Difficult words

bias — To think unfairly about someone or something.

biased, biases

evaluate — To judge or assess something.

fairness — The quality of being just and impartial.

nationality — The state of being a citizen of a country.

researcher — A person who studies a topic carefully.

Researchers

author — A person who writes a text.

authors, author's

Tip: hover, focus or tap highlighted words in the article to see quick definitions while you read or listen.

28 Mar 2026

Disposable gloves can cause false microplastic counts

University of Michigan researchers found that coatings on disposable nitrile and latex gloves can leave stearate residues that look like microplastics. The contamination can affect filters and slides used for air, water and other samples.

Level

Read

29 Apr 2026

AI tool flags children at risk of ADHD early

A study found that an AI model can use routine electronic health records to estimate a child’s risk of ADHD years before a typical diagnosis. The tool flags children for earlier attention but does not give a diagnosis.

Level

Read

29 Dec 2025

Virtual reality near‑death simulation reduces fear of death

A small pilot study found a single short virtual reality simulation of a near‑death experience sharply reduced death anxiety in architecture students. Most participants reported lower stress, though a few felt more anxious.

Level

Read

10 Mar 2026

AI chatbots can shift political opinions

A new study finds that ordinary AI chatbot summaries can change people’s social and political opinions. The researchers say subtle framing comes from latent biases in model training and from how responses are prompted.

Level

Read

5 Nov 2025

Inequality and Pandemics: Why Science Alone Is Not Enough

Matthew M. Kavanagh says science can detect viruses and make vaccines fast, but rising inequality makes pandemics worse. He proposes debt relief, shared technology, regional manufacturing and stronger social support to stop future crises.

Level

Read

LLMs change judgments when told who wrote a text^{CEFR A1}

Difficult words

Discussion questions

Related articles

Disposable gloves can cause false microplastic counts

AI tool flags children at risk of ADHD early

Virtual reality near‑death simulation reduces fear of death

AI chatbots can shift political opinions

Inequality and Pandemics: Why Science Alone Is Not Enough

LLMs change judgments when told who wrote a text CEFR A1

Difficult words

Discussion questions

Related articles

Disposable gloves can cause false microplastic counts

AI tool flags children at risk of ADHD early

Virtual reality near‑death simulation reduces fear of death

AI chatbots can shift political opinions

Inequality and Pandemics: Why Science Alone Is Not Enough

LLMs change judgments when told who wrote a text^{CEFR A1}