Modelling Political Coalition Negotiations Using LLM-based Agents

arXiv:2402.11712v1 Announce Type: new
Abstract: 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 …

abstract agents arxiv coalition communications cs.cl data domain interactions language language processing llm modelling natural natural language natural language processing negotiations nlp paper parties political processing significance type