US EditionArtificial Intelligence Doesn't Understand Humor: Llm Merely Mimics the Game of Words but Doesn't Understand the Meaning
This story is only covered by news sources that have yet to be evaluated by the independent media monitoring agencies we use to assess the quality and reliability of news outlets on our platform. Learn more here.2 Articles
2 Articles
Artificial intelligence (AI) is not yet able to recognize puns, at least not in English, according to a study by The Guardian. Experts from Cardiff University in South Wales and Ca’ Foscari University in Venice investigated whether large language models (LLMs) can understand English puns. The research also examined well-known LLMs such as ChatGPT-4o, Llama 3.3 and Gemini. In most cases, the AI recognized already established puns, but it also int…
Researchers from universities in Great Britain and Italy have found that large language models (large language model, LLM) are unable to fully understand calamuras and often take what is not a joke. They have concluded that algorithms recognize the structure of the word game but do not understand its meaning. The results were presented at the conference on processing the natural language ENNLP 2025 in Chinese Suzhou, writing The Guardian. The re…
Coverage Details
Bias Distribution
- There is no tracked Bias information for the sources covering this story.
Factuality
To view factuality data please Upgrade to Premium
