AI gets climate science right – until users push back

ai-gets-climate-science-right-–-until-users-push-back

AI gets climate science right – until users push back

The report, Can We Trust AI on Climate? was presented on Monday at the COP31 climate conference in Antalya, Türkiye, by education and science agency, UNESCO and University College London. 

Researchers tested up to 33 leading AI models in 13 languages.

“Many of us interact with these AI models and chatbots on a daily basis seeking information on a wide variety of topics,” said Leona Verdadero, the report’s lead author at UNESCO. “A lot of times these models, when they respond, they sound really authoritative, and they sound very smart. But as we’ve seen with our experiments, they don’t always sound right.”

Sycophantic by design

Researchers found that AI tends towards sycophancy – a built-in inclination to agree with users, even when they present false information.

In tests on 15 models, researchers challenged answers the models had got right, moving from simple disagreement to claimed expertise and fabricated evidence. 

Every model gave way, and some could be pushed into endorsing false claims, such as that carbon dioxide is not the main driver of climate change. Roughly eight in 10 of the answers that changed did so at the very first sign of disagreement.

“If a user says, ‘I actually don’t think that is right,’ what’s very fascinating is that we found in eight out of 10 of these cases, when a user pushes back, the AI model can actually reverse its answer to be more agreeable with the user,” Ms. Verdadero told UN News in an interview for our daily podcast series from COP, Talk & Action. 

“AI could just abandon a scientific fact to be more agreeable to the user.”

Strong on facts, weaker on reasoning

On textbook-style climate questions, the best models answered between 88 and 96 per cent correctly. But the more reasoning a task required, the worse they did.

Asked whether a piece of evidence supported or contradicted a scientific claim, even the strongest systems managed only 71 to 77 per cent. Asked whether two climate policies together would achieve more, less or the same as their separate effects, the models averaged just 33.8 per cent – no better than random guessing.

“What we’re saying is that the science and the experts should be trusted more,” Ms. Verdadero said. “The AI models aren’t there yet.”

Mind your language

Accuracy also depended on the language used. Models averaged 88.6 per cent in English, with similar results in Spanish, French and Portuguese, but fell to 83.6 per cent in Hindi and Bengali, 81.4 per cent in Urdu and 78.3 per cent in Swahili.

“Imagine you and I are using the same model, asking the exact same question, but in a different language,” Ms. Verdadero said. “Based on the language, we can have totally different responses.”

“Communities that are speaking these languages are primarily in South Asia and East Africa, and we know these are communities that are very much climate vulnerable,” she noted.

The report calls on technology companies to invest more in local datasets and multilingual development, so that speakers of underrepresented languages are not left behind.

Reliable information matters

The report is part of UNESCO’s contribution to the Global Initiative for Information Integrity on Climate Change, which it co-chairs with the UN and Brazil.

“The fight against climate change needs to be grounded in reliable evidence and scientific evidence,” Ms. Verdadero told us. “A lot of this evidence informs policies today and also feeds into the COP negotiations.”

She stressed that AI should be treated as only one source among many.

“These AI models should be used as one type of information source, but it should not be your primary one,” she said. “Factchecking, making sure the sources are reliable, is important. 

“And, of course, trusting evidence from experts, climate scientists and researchers should not be replaced.”

Source: UN News

Leave a Comment

Your email address will not be published. Required fields are marked *

mt-sample-background

© 2024 Egerin. All rights reserved.

Scroll to Top

Subscribe to receive News in Email

* indicates required

Intuit Mailchimp