Large Language Models for Designing Participatory Budgeting Rules
This work addresses the problem of automating rule design for participatory budgeting, which is used in cities worldwide, by leveraging LLMs to improve utility without sacrificing fairness, representing an incremental advancement in algorithmic design.
The paper tackles the challenge of designing participatory budgeting rules that balance utility and fairness by introducing LLMRule, a framework that uses large language models in an evolutionary search to automate rule design, and demonstrates that LLM-generated rules outperform existing handcrafted rules in utility while maintaining similar fairness on over 600 real-world instances.
Participatory budgeting (PB) is a democratic paradigm for deciding the funding of public projects given the residents' preferences, which has been adopted in numerous cities across the world. The main focus of PB is designing rules, functions that return feasible budget allocations for a set of projects subject to some budget constraint. Designing PB rules that optimize both utility and fairness objectives based on agent preferences had been challenging due to the extensive domain knowledge required and the proven trade-off between the two notions. Recently, large language models (LLMs) have been increasingly employed for automated algorithmic design. Given the resemblance of PB rules to algorithms for classical knapsack problems, in this paper, we introduce a novel framework, named LLMRule, that addresses the limitations of existing works by incorporating LLMs into an evolutionary search procedure for automating the design of PB rules. Our experimental results, evaluated on more than 600 real-world PB instances obtained from the U.S., Canada, Poland, and the Netherlands with different representations of agent preferences, demonstrate that the LLM-generated rules generally outperform existing handcrafted rules in terms of overall utility while still maintaining a similar degree of fairness.