Polish to be the most effective language for prompting AI, new study reveals

Polish to be the most effective language for prompting AI, new study reveals

• 2025年11月1日下午7:38

2 min de lecture

Out of 26 different languages, Polish proved to be the most effective for prompting artificial intelligence (AI) models, with English only ranking sixth, a study by The University of Maryland (UMD) and Microsoft revealed.

"Our experiment yielded some surprising and unintuitive findings. Firstly, English did not perform best across all models, in fact it came sixth out of 26 languages when long texts were assessed, while Polish proved to be the leading language," the authors of the report wrote.

A team of researchers tested how well several major AI language models, including OpenAI, Google Gemini, Qwen, Llama and DeepSeek, responded to identical inputs in 26 different languages.

The results showed that Polish had an average accuracy of 88% in completing the tasks.

"As the analysis shows, it is the most precise in terms of giving commands to artificial intelligence. Until now, Polish was widely regarded as one of the most difficult languages to learn. As it turns out, humans have trouble with it, but not AI," the Polish Patent Office wrote in a Facebook post.

Interestingly, AI systems demonstrated a strong understanding of Polish, even though the amount of Polish-language data available for training is far smaller than that for English or Chinese.

In comparison, Chinese performed notably poorly, ranking fourth from the bottom out of the 26 languages tested.

The top 10 most effective languages for conversational AI were as follows:

- Polish 88%

- French 87%

- Italian 86%

- Spanish 85%

- Russian 84%

- English 83.9%

- Ukrainian 83.5%

- Portuguese 82%

- German 81%

- Dutch 80%

Uzbekistan strengthens labour rights through union-led reforms

• 下午4:57

Uzbekistan’s trade unions mark 120 years of operation, by taking the lead in labour reform, pushing for equal pay, safer workplaces, and stronger employee rights.

Most safety precautions for AI tools can be bypassed within a few minutes, study finds

• 下午3:52

AI systems ‘forget’ their safety measures the longer a user speaks to it, making the tools more likely to give out harmful or inappropriate information, a new report found.

French competition authority slaps €4.6 million fine on telehealth app Doctolib for unfair practices

• 下午3:17

France’s competition authority slapped a €4.6 million fine on telehealth firm Doctolib for what it said was anticompetitive behaviour.

Germany fines JPMorgan €45 million for anti-money-laundering failings

• 下午2:26

Germany’s financial watchdog BaFin has imposed a record fine on JPMorgan for systemic failings in its anti-money-laundering controls.

Radiation therapy does not improve survival rates for some women with breast cancer, study finds

• 下午1:24

A new international study found that radiation therapy did not affect 10-year survival rates for women with early-stage breast cancer who were considered “intermediate risk”.

EU Tech Commissioner meets French ministers over Shein 'sex doll' uproar

• 下午1:17

French ministers urge the European Commission to sanction e-commerce giant Shein for allowing illegal items to be sold on its website including a 'childlike sex doll' that sparked a national scandal.

Chipmaker Nexperia said it halted China shipments on payment refusal

• 上午10:42

Dutch chipmaker Nexperia said it stopped sending wafers to its Chinese unit because of a payment refusal — the latest twist in Europe’s semiconductor standoff with Beijing.

'Vibe coding' named Word of the Year by Collins Dictionary

• 上午9:45

“Vibe coding”, an emerging software development that turns natural language into computer code using AI, has been named Collins Dictionary’s Word of the Year for 2025.

How Denmark is trying to protect citizens from AI deepfakes

• 上午9:36

Denmark is seeking to protect ordinary Danes, as well as performers and artists who might have their appearance or voice imitated and shared without their permission.

Chinese-made buses in Norway can be halted remotely, spurring increased security

• 上午8:58

Test results showed that the Chinese bus maker had access to the vehicles' control systems for software updates and diagnostics.

Heavy drinkers at higher risk of brain bleeds in old age, study finds

• 上午6:00

Heavy drinkers were aged 64 on average when they had a stroke, compared to 75 among people who drank less alcohol.

Nvidia first to hit $5 trillion valuation but last in AI supply chain decarbonisation, study finds

• 上午6:00

The rapid growth of the AI market comes with increasing environmental challenges. The massive energy demands are raising serious concerns. Leading AI companies, including Nvidia, have so far failed to address these issues according to Greenpeace.