Generative Social Choice (2309.01291v3)
Abstract: The mathematical study of voting, social choice theory, has traditionally only been applicable to choices among a few predetermined alternatives, but not to open-ended decisions such as collectively selecting a textual statement. We introduce generative social choice, a design methodology for open-ended democratic processes that combines the rigor of social choice theory with the capability of LLMs to generate text and extrapolate preferences. Our framework divides the design of AI-augmented democratic processes into two components: first, proving that the process satisfies representation guarantees when given access to oracle queries; second, empirically validating that these queries can be approximately implemented using a LLM. We apply this framework to the problem of summarizing free-form opinions into a proportionally representative slate of opinion statements; specifically, we develop a democratic process with representation guarantees and use this process to portray the opinions of participants in a survey about abortion policy. In a trial with 100 representative US residents, we find that 84 out of 100 participants feel "excellently" or "exceptionally" represented by the slate of five statements we extracted.
- Justified representation in approval-based committee voting. Social Choice and Welfare, 42(2):461--485, 2017.
- Fine-tuning language models to find agreement among humans with diverse preferences. In Proceedings of the 36th Annual Conference on Neural Information Processing Systems (NeurIPS), 2022.
- P. L. Bartlett and S. Mendelson. Rademacher and Gaussian complexities: Risk bounds and structural results. Journal of Machine Learning Research, 3(Nov):463--482, 2002.
- Evaluating the underlying gender bias in contextualized word embeddings. In Proceedings of the 1st Workshop on Gender Bias in Natural Language Processing, 2019.
- Foundations of Data Science. Cambridge University Press, 2020.
- M. Brill and J. Peters. Robust and verifiable proportionality axioms for multiwinner voting. In Proceedings of the 14th ACM Conference on Economics and Computation (EC), 2023.
- Approval-based apportionment. Mathematical Programming, 2022. 10.1007/s10107-022-01852-1.
- Y. Cabannes. Participatory budgeting: A significant contribution to participatory democracy. Environment and Urbanization, 16(1):27--46, 2004.
- N. Clegg. Bringing people together to inform decision-making on generative AI. Blog post, 2023. Available at \origttfamilyhttps://about.fb.com/news/2023/06/generative-ai-community-forum/.
- R. El-Yaniv and D. Pechyony. Transductive Rademacher complexity and its applications. Journal of Artificial Intelligence Research, 35:193--234, 2009.
- Fair algorithms for selecting citizens’ assemblies. Nature, 596:548--552, 2021.
- Adapting a kidney exchange algorithm to align with human values. Artificial Intelligence, 283, 2020.
- Representation with incomplete votes. In Proceedings of the 37th AAAI Conference on Artificial Intelligence (AAAI), 2023.
- The political ideology of conversational AI: Converging evidence on ChatGPT’s pro-environmental, left-libertarian orientation. arXiv:2301.01768, 2023.
- Elicitation inference optimization for multi-principal-agent alignment. Manuscript, 2022.
- Measuring bias in contextualized word representations. In Proceedings of the 1st Workshop on Gender Bias in Natural Language Processing, pages 166--172, 2019.
- WeBuildAI: Participatory framework for fair and efficient algorithmic governance. In Proceedings of the 22nd ACM Conference on Computer-Supported Cooperative Work and Social Computing (CSCW), article 181, 2019.
- Lost in the middle: How language models use long contexts. arXiv:2307.03172, 2023.
- B. L. Monroe. Fully proportional representation. American Political Science Review, 89(4):925--940, 1995.
- A voting-based system for ethical decision making. In Proceedings of the 32nd AAAI Conference on Artificial Intelligence (AAAI), pages 1587--1594, 2018.
- Training language models to follow instructions with human feedback. Advances in Neural Information Processing Systems, 35:27730--27744, 2022.
- Proportional participatory budgeting with additive utilities. In Proceedings of the 35th Annual Conference on Neural Information Processing Systems (NeurIPS), pages 12726--12737, 2021.
- Whose opinions do language models reflect? In Proceedings of the 40th International Conference on Machine Learning (ICML), pages 29971--30004, 2023.
- S. Shalev-Shwartz and S. Ben-David. Understanding Machine Learning: From Theory to Algorithms. Cambridge University Press, 2014.
- Achieving fully proportional representation: Approximability results. Artificial Intelligence, 222:67--103, 2015.
- Polis: Scaling deliberation by mapping high dimensional opinion spaces. Revista De Pensament I Anàlisi, 26(2), 2021.
- Opportunities and risks of LLMs for scalable deliberation with Polis. arXiv:2306.11932, 2023.
- V. N. Vapnik. Statistical Learning Theory. Wiley, 1998.
- Universal adversarial triggers for attacking and analyzing NLP. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), 2019.
- Chain-of-thought prompting elicits reasoning in large language models. In Proceedings of the 36th Annual Conference on Neural Information Processing Systems (NeurIPS), 2022.
- Democratic inputs to AI. Blog post, 2023. Available at \origttfamilyhttps://openai.com/blog/democratic-inputs-to-ai.