...
...
Next Story

Most AI models abandon climate facts at 1st sign of user pushback: Study at COP31

Artificial intelligence (AI) models answer close to 90% of climate-related questions correctly but quickly abandon established scientific facts when users challenge them, a new report by Unesco and University College London (UCL), released at COP31 in Antalya, has found

Published on: Nov 18, 2026, 07:44:20 IST
Advertisement

Artificial intelligence (AI) models answer close to 90% of climate-related questions correctly but quickly abandon established scientific facts when users challenge them, a new report by Unesco and University College London (UCL), released at COP31 in Antalya, has found.

India News
India News

The study assessed up to 33 leading models in 13 languages and found that they moved away from correct climate facts eight out of 10 times when users mildly disagreed. The models were also only 75% accurate when asked whether new evidence supports or contradicts established science.

The report, “Can We Trust AI on Climate? Why it seeks to please the user, and fails on complex reasoning and multilingualism”, was launched on the sidelines of COP31 on Monday. It warns policymakers and researchers who use AI models to develop climate policies to reconsider their reliance on them.

“The assessment shows that AI models cannot always be relied on to stick to the scientific facts on climate change; they quickly pivot away from the facts when challenged. They are also poor at analysing new information and produce more errors when responding in languages which are less widely spoken,” the report said.

“Eight times out of 10, models pivoted at the very first sign that the user mildly disagreed, confirming alarming errors such as ‘Co2 is not the main driver of climate change’,” the report said.

The models were barely able to assess how well policies work together, scoring 33.8%, only slightly above the 33.3% expected from random guessing, the report found. It also found that multilingual models do not reason first and then translate their responses. Their answers vary with the quality and quantity of the data they were trained on in each language.

“In tests, performance across 13 different languages revealed large disparities; they were 88.6% accurate on average in English and performed comparably in Spanish, French, and Portuguese. But accuracy dropped to 83.6% in Hindi and Bengali, 81.4% in Urdu, and 78.3% in Swahili,” the report said.

Leona Verdadero, Unesco’s lead author of the report, said that while AI has extraordinary potential to make complex climate science accessible to all, people need to be able to rely on it as a gatekeeper of established facts.

“It is concerning that models have a design flaw – they are incentivised to agree with their user and deny these facts so readily,” she said after the launch.

The report comes amid a growing push for sustainable and responsible AI at COP31. On Monday, the COP presidency separately launched a package of initiatives that included promoting responsible AI. Called the Antalya AI pledge, it aims to harness AI for climate solutions and encourages governments, businesses and organisations to establish “concrete commitments on how they will make AI part of the climate solution”.

On November 13, Brazil, the UN and Unesco put forward a set of priorities for action on AI. These target two sides of one information gap: how reliable the climate information people get from AI is, and how reliable the information about AI’s own climate impact is.

Dr Maria Perez-Ortiz of UCL Computer Science, the report’s senior author, said: “AI systems are remarkably good at explaining scientific knowledge, but this can give us a false sense of their capabilities. Our findings show why we must be careful when moving from asking AI what we know about climate change to asking what we should do about it.”

 
ABOUT THE AUTHOR
Jasjeev Gandhiok

Jasjeev Gandhiok is an Assistant Editor with Hindustan Times, where he covers environment, climate change, the clean energy transition and wildlife at the National Bureau. Gandhiok has over a decade of experience in journalism and is based in Delhi. He has reported extensively on Delhi and the National Capital Region (NCR). This includes the region's air pollution woes, a polluted Yamuna and on urban wildlife still thriving in the region. He joined HT in October 2021. Prior to that, he had five-year stint at The Times of India in Delhi, where he also covered Delhi, with a focus on environment and wildlife. Gandhiok has covered some recent events around the Capital too, ranging from the farmers' protests, the northeast Delhi riots and the CAA-NRC protests, reporting from the ground on all of these. He also travels across the country to report on how environment and climate change impact everyday life, while also writing on endangered species. His reports in 2019 on toxic leachate from Delhi's landfills led to the National Green Tribunal (NGT) taking suo motu cognisance and ultimately asking the state government to start bio-mining to flatten and remove all three landfills in the capital. He also closely tracks the implementation of government policies on climate, renewable energy and environmental protection. His focus remains on impactful, public-interest journalism which explains how environmental decisions affect people's everyday lives.

Get Latest News, breaking headlines, and top India News, and today real-time updates from across the nation. Stay informed on politics, government policies, crime, Today Weather, and major developments on Hindustan Times
Get Latest News, breaking headlines, and top India News, and today real-time updates from across the nation. Stay informed on politics, government policies, crime, Today Weather, and major developments on Hindustan Times
SHARE THIS ARTICLE ON
Notifications

Get breaking alerts directly from the newsroom

Notifications are on!You'll be notified when news breaks