{"id":139682,"date":"2025-07-09T09:30:20","date_gmt":"2025-07-09T07:30:20","guid":{"rendered":"https:\/\/diaridigital.urv.cat\/?p=139682"},"modified":"2025-07-28T13:03:46","modified_gmt":"2025-07-28T11:03:46","slug":"removing-information-from-ai","status":"publish","type":"post","link":"https:\/\/diaridigital.urv.cat\/en\/removing-information-from-ai\/","title":{"rendered":"Removing information from AI models is more difficult than it sounds"},"content":{"rendered":"

Researchers at the Universitat Rovira i Virgili have studied the effectiveness of unlearning <\/em>techniques in artificial intelligence models. These strategies seek to eliminate personal, incorrect or discriminatory data from large language models such as ChatGPT, Mixtral, Bard or Copilot, among others. The analysis reveals that there is currently no method that guarantees total and irreversible erasure, other than retraining the model without the data in question, a very costly and inefficient process. This creates a conflict with the right to be forgotten, which is enshrined in European legislation and which obliges data controllers to delete people’s personal data upon request. The solution to this incompatibility, they argue, is to design new ways of training models that facilitate unlearning <\/em>with guarantees.<\/p>\n

The performance of artificial intelligence (AI) models – also called large language models (LLMs) – depends on the data they are trained on. The companies that run them feed them with as much information as they can from as wide a range of sources as possible to make them more powerful and, above all, better than their competitors. These are huge models with billions of parameters and they know many, many things. “In some cases, they even know things that, for various reasons, they should not know,” explains Josep Domingo, researcher at the Department of Computer Engineering and Mathematics and co-author of the research.<\/p>\n

\"\"<\/a>
David S\u00e1nchez i Josep Domingo, investigadors del Departament d’Enginyeria Inform\u00e0tica i Matem\u00e0tiques, autors de la recerca.<\/figcaption><\/figure>\n

So what happens when an AI model has been fed with copyrighted works – could it mimic the style of a particular writer and write a sequel to the latest bestseller? And, if the model has personal information, does it know if someone has been ill, taken sick leave or just bought, say, a flat? Fortunately, we have legal mechanisms to protect all this data, such as the Spanish Intellectual Property Law or the European Union’s General Data Protection Regulation (GDPR).<\/p>\n

The GDPR regulates the processing of personal data of any natural person in the European Union and includes, among other aspects, the right to be forgotten. Therefore, when data controllers receive any request to remove personal data from their systems, they have to comply. And that includes all companies with AI models operating in Europe. However, the way these models have been configured makes deleting specific data a much more complex technical challenge than it might seem.<\/p>\n

Against this backdrop, researchers from the CRISES Research Group have studied the ability of large language models to unlearn <\/em>and the computational cost of doing so. There are mainly two approaches to removing knowledge from an AI model. The first option is the most rudimentary and involves removing all the knowledge and training the model again without the data that you want to eliminate. “This is an impractical and computationally very costly process, but it is currently the only way to guarantee one hundred per cent removal,” says David S\u00e1nchez, researcher at the Department of Computer Engineering and Mathematics and co-author of the study.<\/p>\n

The other approach to unlearning <\/em>involves getting the model to forget specific information, which avoids the need to retrain the model from scratch every time some information needs to be removed. The underlying problem, according to the researchers, is that nobody fully understands how LLMs work, not even the people who have designed them. Although it is known how to train them and how to make them more efficient and accurate, there is no way of knowing in which region of the model a particular piece of information resides. S\u00e1nchez warns, however, that the aforementioned methods, although much more efficient, do not fully ensure unlearning <\/em>and reminds us that the Regulation is very clear and requires absolute safeguards<\/em> to be put in place.<\/p>\n