Modelling Political Coalition Negotiations Using LLM-based Agents
This work addresses the lack of data and modelling in political negotiation for researchers in NLP and political science, though it is incremental in applying existing LLMs to a new domain.
The paper tackles the problem of modelling political coalition negotiations by introducing it as a novel NLP task and using LLM-based agents, resulting in the creation of the POLCA dataset and a hierarchical Markov decision process for simulation and outcome prediction.
Coalition negotiations are a cornerstone of parliamentary democracies, characterised by complex interactions and strategic communications among political parties. Despite its significance, the modelling of these negotiations has remained unexplored with the domain of Natural Language Processing (NLP), mostly due to lack of proper data. In this paper, we introduce coalition negotiations as a novel NLP task, and model it as a negotiation between large language model-based agents. We introduce a multilingual dataset, POLCA, comprising manifestos of European political parties and coalition agreements over a number of elections in these countries. This dataset addresses the challenge of the current scope limitations in political negotiation modelling by providing a diverse, real-world basis for simulation. Additionally, we propose a hierarchical Markov decision process designed to simulate the process of coalition negotiation between political parties and predict the outcomes. We evaluate the performance of state-of-the-art large language models (LLMs) as agents in handling coalition negotiations, offering insights into their capabilities and paving the way for future advancements in political modelling.