AI Challenge
AI Challenges aim to bring together multidisciplinary teams of policymakers, diplomats, foreign policy practitioners, data scientists to develop cutting-edge solutions that can potentially assist and augment the work of foreign policy professionals.
LEVERAGING LLMS IN ENHANCING MULTILATERAL NEGOTIATIONS
November 2023 - January 2024
This project, conducted in partnership with Omdena, leveraged cutting-edge Large Language Models (LLMs) and advanced techniques to address challenges faced by foreign policy experts in navigating complex negotiations. Specifically, we developed a Proof of Concept AI assistant to help policy officers summarize a large number of policy documents and make queries from these documents. Focusing on the UN's Global Digital Compact (GDC) negotiations as a test case, the project successfully illustrates the benefits of integrating AI tools into the workflows of policy officers. We are delivering a Proof of Concept (PoC) system suitable for beta testing, which is also a solid foundation for a widely deployable production system should further development work be pursued.
BACKGROUND
As the world grapples with unprecedented challenges, including geopolitical conflicts and humanitarian crises, the need for innovative, data-driven diplomacy is more urgent than ever. Advancements in AI and natural language processing hold the potential for transformative impacts on negotiations and mediation practices. This AI Challenge aims to explore the integration of such technologies into diplomacy, facilitating more informed decision-making and efficient negotiation processes.
FORMAT
The AI Challenge spanned over 10 weeks, combining intense brainstorming sessions, workshops, and hands-on machine learning work. Participants explored and searched for relevant datasets, and built AI tools, to respond to a specific diplomacy problem.
​
PARTICIPANTS
This challenge engaged 50 participants, field experts and AI experts from various parts of the world.