Addressing the alignment problem in transportation policy making: an LLM approach
Fuente:
arXiv
Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866918176281853952 |
|---|---|
| author | Yan, Xiaoyu Dai, Tianxing Nie, Yu Marco |
| author_facet | Yan, Xiaoyu Dai, Tianxing Nie, Yu Marco |
| contents | A key challenge in transportation planning is that the collective preferences of heterogeneous travelers often diverge from the policies produced by model-driven decision tools. This misalignment frequently results in implementation delays or failures. Here, we investigate whether large language models (LLMs), noted for their capabilities in reasoning and simulating human decision-making, can help inform and address this alignment problem. We develop a multi-agent simulation in which LLMs, acting as agents representing residents from different communities in a city, participate in a referendum on a set of transit policy proposals. Using chain-of-thought reasoning, LLM agents provide ranked-choice or approval-based preferences, which are aggregated using instant-runoff voting (IRV) to model democratic consensus. We implement this simulation framework with both GPT-4o and Claude-3.5, and apply it for Chicago and Houston. Our findings suggest that LLM agents are capable of approximating plausible collective preferences and responding to local context, while also displaying model-specific behavioral biases and modest divergences from optimization-based benchmarks. These capabilities underscore both the promise and limitations of LLMs as tools for solving the alignment problem in transportation decision-making. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_13139 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Addressing the alignment problem in transportation policy making: an LLM approach Yan, Xiaoyu Dai, Tianxing Nie, Yu Marco Computers and Society Computational Engineering, Finance, and Science Computation and Language Multiagent Systems A key challenge in transportation planning is that the collective preferences of heterogeneous travelers often diverge from the policies produced by model-driven decision tools. This misalignment frequently results in implementation delays or failures. Here, we investigate whether large language models (LLMs), noted for their capabilities in reasoning and simulating human decision-making, can help inform and address this alignment problem. We develop a multi-agent simulation in which LLMs, acting as agents representing residents from different communities in a city, participate in a referendum on a set of transit policy proposals. Using chain-of-thought reasoning, LLM agents provide ranked-choice or approval-based preferences, which are aggregated using instant-runoff voting (IRV) to model democratic consensus. We implement this simulation framework with both GPT-4o and Claude-3.5, and apply it for Chicago and Houston. Our findings suggest that LLM agents are capable of approximating plausible collective preferences and responding to local context, while also displaying model-specific behavioral biases and modest divergences from optimization-based benchmarks. These capabilities underscore both the promise and limitations of LLMs as tools for solving the alignment problem in transportation decision-making. |
| title | Addressing the alignment problem in transportation policy making: an LLM approach |
| topic | Computers and Society Computational Engineering, Finance, and Science Computation and Language Multiagent Systems |
| url | https://arxiv.org/abs/2510.13139 |