2000 character limit reached
Modelling Political Coalition Negotiations Using LLM-based Agents (2402.11712v1)
Published 18 Feb 2024 in cs.CL
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 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 LLM-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 LLMs as agents in handling coalition negotiations, offering insights into their capabilities and paving the way for future advancements in political modelling.
- Llm-deliberation: Evaluating llms with interactive multi-agent negotiation games. arXiv preprint arXiv:2309.17234.
- Gpt-4 technical report. arXiv preprint arXiv:2303.08774.
- The fulfilment of election pledges in india. Journal of Contemporary Asia, 54(1):133–151.
- Open-source large language models outperform crowd workers and approach chatgpt in text-annotation tasks. arXiv preprint arXiv:2307.02179.
- Analysis of political sentiment orientations on twitter. Procedia Computer Science, 167:1821–1828.
- We can detect your bias: Predicting the political ideology of news articles. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 4982–4991.
- How well can llms negotiate? negotiationarena platform and analysis. arXiv preprint arXiv:2402.05863.
- Bundestag-mine: Natural language processing for extracting key information from government documents. In Legal Knowledge and Information Systems, pages 391–394. IOS Press.
- Predicting the vote using legislative speech. In Proceedings of the 19th annual international conference on digital government research: governance in the data age, pages 1–10.
- Charles Chang and Michael Masterson. 2020. Using word order in political text classification with long short-term memory models. Political Analysis, 28(3):395–411.
- Casino: A corpus of campsite negotiation dialogues for automatic negotiation systems. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies.
- Cooper: Coordinating specialized agents towards a complex dialogue goal. arXiv preprint arXiv:2312.11792.
- Rory Costello and Robert Thomson. 2008. Election pledges and their enactment in coalition governments: A comparative analysis of ireland. Journal of Elections, Public Opinion and Parties, 18(3):239–256.
- Alejandro Ecker and Thomas M Meyer. 2020. Coalition bargaining duration in multiparty democracies. British Journal of Political Science, 50(1):261–280.
- Improving language model negotiation with self-play and in-context learning from ai feedback. arXiv preprint arXiv:2305.10142.
- Chatgpt outperforms crowd-workers for text-annotation tasks. arXiv preprint arXiv:2303.15056.
- Significant Gravitas. 2023. Autogpt: the heart of the open-source agent ecosystem.
- Isabelle Guinaudeau and Elisa Deiss-Helbig. 2020. From electoral pledges to coalition agreements: Coalition bargaining and policy payoffs in germany (2005-2017). In ECPR General Conference.
- Language of bargaining. arXiv preprint arXiv:2306.07117.
- Political ideology detection using recursive neural networks. In Proceedings of the 52nd annual meeting of the Association for Computational Linguistics (volume 1: long papers), pages 1113–1122.
- Billion-scale similarity search with GPUs. IEEE Transactions on Big Data, 7(3):535–547.
- Coalition Agreements as Control Devices: Coalition Governance in Western and Eastern Europe. Oxford University Press.
- Heike Klüver and Hanna Bäck. 2019. Coalition agreements, issue attention, and cabinet governance. Comparative Political Studies, 52(13-14):1995–2031.
- COALITIONAGREE Dataset.
- Svenja Krauss and Heike Kluever. 2023. Cabinet formation and coalition governance: The effect of portfolio allocation on coalition agreements. Government and Opposition, 58(4):862–881.
- The manifesto data collection. manifesto project (mrg/cmp/marpor).
- Encouraging divergent thinking in large language models through multi-agent debate. arXiv preprint arXiv:2305.19118.
- Politics: Pretraining with same-story article comparison for ideology prediction and stance detection. Findings of the Association for Computational Linguistics: NAACL 2022.
- Charles M Macal and Michael J North. 2005. Tutorial on agent-based modeling and simulation. In Proceedings of the Winter Simulation Conference, 2005., pages 14–pp. IEEE.
- Coalition dynamics: advances in the study of the coalition life cycle. West european politics, 47(1):1–30.
- Salomon Orellana and Halil Bisgin. 2023. Using natural language processing to analyze political party manifestos from new zealand. Information, 14(3):152.
- Generative agents: Interactive simulacra of human behavior. arXiv preprint arXiv:2304.03442.
- Deliberative democracy in an unequal world: A text-as-data study of south india’s village assemblies. American Political Science Review, 113(3):623–640.
- Can language models teach weaker agents? teacher explanations improve students via theory of mind. arXiv preprint arXiv:2306.09299.
- Mauricio Salgado and Nigel Gilbert. 2013. Agent based modelling. In Handbook of quantitative methods for educational research, pages 247–265. Brill.
- Bad news or mad news? sentiment scoring of negativity, fear, and anger in news content. The ANNALS of the American Academy of Political and Social Science, 659(1):108–121.
- Kaare Strøm and Wolfgang C Müller. 1999. The keys to togetherness: Coalition agreements in parliamentary democracies. The Journal of Legislative Studies, 5(3-4):255–282.
- Petter Törnberg. 2023. Chatgpt-4 outperforms experts and crowd workers in annotating political twitter messages with zero-shot learning. arXiv preprint arXiv:2304.06588.
- Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971.
- Attacking fake news detectors via manipulating news social engagement. arXiv preprint arXiv:2302.07363.
- A survey on large language model based autonomous agents. arXiv preprint arXiv:2308.11432.
- Principal component analysis. Chemometrics and intelligent laboratory systems, 2(1-3):37–52.
- From policy-making statements to first-order logic. In Electronic Government and the Information Systems Perspective: First International Conference, EGOVIS 2010, Bilbao, Spain, August 31–September 2, 2010. Proceedings 1, pages 47–61. Springer.
- A survey of large language models. arXiv preprint arXiv:2303.18223.
- Fake news detection via nlp is vulnerable to adversarial attacks. arXiv preprint arXiv:1901.09657.
Paper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.
Top Community Prompts
Collections
Sign up for free to add this paper to one or more collections.