Beyond ChatGPT: What are the opportunities and risks of advanced artificial intelligence (AI) systems for child rights?

By Nwando Dike , Carolin Frankenhauser and Juan M. Merlos , UNICEF's Information and Communication Technology Division.

It is 2023 and everyone is talking about artificial intelligence (AI). New chatbots that interact with its users in a conversational way, such as ChatGPT and Bard, are disrupting industries and many parts of society. Since its launch in November 2022, ChatGPT has sparked debate about the risks and opportunities of highly advanced AI systems. This debate is not new: UNICEF has researched the intersection between AI and child rights extensively and developed a range of guidance documents for policymakers and the private sector on the subject.

With the rise of ChatGPT, we revisited the subject and asked ourselves: What are the potential ways to use advanced AI applications for UNICEF and realize the rights of children everywhere? If developed ethically and used responsibly, can they deliver impact for children? And more importantly: What are the risks and how do we mitigate them? 

Transforming community engagement  

Chatbots such as ChatGPT are a powerful tool for community engagement. In over 116 countries, UNICEF uses RapidPro, an open-source platform that allows users to scale mobile services for messaging and real-time data collection in vital areas such as health, education, Water and Sanitation, and Child Protection. Through RapidPro, UNICEF, governments, and NGO partners can easily build and scale mobile applications to engage with frontline workers, youth, and communities and for national system strengthening. 

RapidPro is also a powerful and intuitive tool for chatbot development and has been used to create mental health, Covid-19 information and health information chatbots, to name a few. As ChatGPT is demonstrating, advanced AI can transform and improve the impact of chatbots in areas such as mental health support, education, and training. UNICEF is already exploring how to apply AI in evolving RapidPro functionality. Cognizant of the risks posed by the use of AI-powered chatbots to children and vulnerable populations, UNICEF also created a Safer Chatbots Implementation Guide to provide guidance on how to safeguard against those risks. 

Rethinking education and training  

The potential and risks of chatbots such as ChatGPT for education are still being explored. Some see ChatGPT as a powerful tool to promote critical thinking, while others worry about its potential to trick teachers. What’s clear from the debate is that students increasingly will need to understand how to work with digital solutions such as ChatGPT to succeed in today’s labor market. This underscores the importance of connecting every school to the internet and making sure that pupils everywhere have the same chance at learning digital skills. The availability and potential of technology mean that digital learning should be part of a basic basket of essential services for every child and young person. We need to connect every child and young person – some 3.5 billion by 2030 – to world-class digital solutions.

Increasing efficiency  

Continuously increasing efficiency and business innovation are key priorities for United Nations agencies. As development financing gaps keep increasing, this objective is more important and timelier than ever. Advanced AI chatbots can speed up project management-related tasks such as content creation. Time saved on these activities could free up resources for more complex, value-adding activities such as engaging with and learning from communities and partners. This however requires that AI systems can ensure the factual accuracy of the content they provide. ChatGPT for example still provides wrong answers to simple questions.  

Improving data availability for program design, monitoring, and evaluation  

Every day, UNICEF collects and uses large amounts of data concerning the state of children everywhere. What if we could use powerful AI solutions to make that data even more easily accessible and searchable? Being able to identify within seconds the number of children, immunization rates, and nutrition data in a specific location might improve decision-making in emergency and data-driven policymaking.  

Safeguarding against risks  

As we continue to explore this topic, many more ways to apply advanced AI, in areas such as safe parenting, antenatal care, and play emerge. Yet the risks become clear quickly: Even the most advanced AI systems are not yet able to eliminate harmful content and language. What’s more: Data that is used to train AI systems is often biased and perpetuates harmful stereotypes. Underrepresented groups may be further excluded in data that is presented as facts, thus exacerbating inequality and exclusion. These are not abstract fears but growing dangers present in many AI systems being used by and for kids today. Furthermore, misinformation can spread on such systems, with very real consequences children. There are also privacy concerns. As these examples show, AI policies that promote child rights are critical: Among other things, these should ensure the inclusion of and for children, protect children’s data and privacy, and ensure their (online) safety.

So, while it is easy to get excited about the rapid advancements in AI, we must be mindful of the consequences for the most vulnerable. (Human) checks and balances, contextualization and other safeguards are indispensable for using chatbots in contexts that affect children. Meanwhile, ChatGPT itself is quite aware of its strengths and limitations. Asked what it can do for child rights, it responded:  

As an AI language model, I do not have the capability to directly take actions to support child rights. However, I can provide information and answer questions related to child rights to raise awareness and promote understanding of the issue. Additionally, I can facilitate conversation and support education on the subject, which could contribute to creating a more informed and engaged community that is better equipped to advocate for and protect the rights of children.