aiqbench analysis
This research addresses the scalability of participatory budgeting by developing privacy-preserving algorithms that effectively shortlist citizen-proposed projects using historical voting data. The study demonstrates that while naive LLM approaches have limitations, a specific vote-based pipeline allows large language models to match classical machine learning performance in predicting funding outcomes. This work highlights the practical application of AI in democratic processes where user preferences remain stable enough for algorithmic approximation.
Algorithmic Shortlisting in Participatory Budgeting
arXiv:2508.06577v4 Announce Type: replace-cross Abstract: Participatory budgeting is a democratic innovation that allows citizens to propose and vote on public investment projects. To help organizers manage large volumes of submissions, we design and test privacy-preserving methods for algorithmic shortlisting. These algorithms predict which projects are likely to be funded using only project features and anonymous historical voting data. We demonstrate the limitations of a naive approach that uses a large language model to rank projects based on past success and propose a vote-based pipeline that enables state-of-the-art LLMs to perform on par with classical machine learning. Our findings indicate that user preferences in participatory budgeting are stable enough to allow algorithmic shortlisting to approximate an initial selection of projects effectively.
Abstract:Participatory budgeting is a democratic innovation that allows citizens to propose and vote on public investment projects. To help organizers manage large volumes of submissions, we design and test privacy-preserving methods for algorithmic shortlisting. These algorithms predict which projects are likely to be funded using only project features and anonymous historical voting data. We demonstrate the limitations of a naive approach that uses a large language model to rank projects based on past success and propose a vote-based pipeline that enables state-of-the-art LLMs to perform on par with classical machine learning. Our findings indicate that user preferences in participatory budgeting are stable enough to allow algorithmic shortlisting to approximate an initial selection of projects effectively.
Computers and Society (cs.CY); Artificial Intelligence (cs.AI)
arXiv:2508.06577 [cs.CY]
(or arXiv:2508.06577v4 [cs.CY] for this version)
https://doi.org/10.48550/arXiv.2508.06577 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 211 words
