LingVo.club
📖+10 XP
🎧+10 XP
+15 XP
LLMs change judgments when told who wrote a text (Level A1) — three white disc on brown surface

LLMs change judgments when told who wrote a textCEFR A1

25 Nov 2025

Level A1 – Beginner
2 min
66 words
  • 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

  • biasTo think unfairly about someone or something.
    biased, biases
  • evaluateTo judge or assess something.
  • fairnessThe quality of being just and impartial.
  • nationalityThe state of being a citizen of a country.
  • researcherA person who studies a topic carefully.
    Researchers
  • authorA 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.

Discussion questions

  • Why do you think AI can be biased?
  • How important is it for AI to be fair?
  • What do you think about AI judging texts?

Related articles

Rising Crop Losses in India (Level A1)
9 Jan 2026

Rising Crop Losses in India

Crop losses in India are increasing because of unseasonal rain, pests, land damage and pollution. Experts warn this hurts farmers, food quality and health, and they call for better measurement and support for farmers.