{"ID":2869452,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.15132","arxiv_id":"2509.15132","title":"From Pixels to Urban Policy-Intelligence: Recovering Legacy Effects of Redlining with a Multimodal LLM","abstract":"This paper shows how a multimodal large language model (MLLM) can expand urban measurement capacity and support tracking of place-based policy interventions. Using a structured, reason-then-estimate pipeline on street-view imagery, GPT-4o infers neighborhood poverty and tree canopy, which we embed in a quasi-experimental design evaluating the legacy of 1930s redlining. GPT-4o recovers the expected adverse socio-environmental legacy effects of redlining, with estimates statistically indistinguishable from authoritative sources, and it outperforms a conventional pixel-based segmentation baseline-consistent with the idea that holistic scene reasoning extracts higher-order information beyond object counts alone. These results position MLLMs as policy-grade instruments for neighborhood measurement and motivate broader validation across policy-evaluation settings.","short_abstract":"This paper shows how a multimodal large language model (MLLM) can expand urban measurement capacity and support tracking of place-based policy interventions. Using a structured, reason-then-estimate pipeline on street-view imagery, GPT-4o infers neighborhood poverty and tree canopy, which we embed in a quasi-experiment...","url_abs":"https://arxiv.org/abs/2509.15132","url_pdf":"https://arxiv.org/pdf/2509.15132v1","authors":"[\"Anthony Howell\",\"Nancy Wu\",\"Sharmistha Bagchi\",\"Yushim Kim\",\"Chayn Sun\"]","published":"2025-09-18T16:42:01Z","proceeding":"cs.CY","tasks":"[\"cs.CY\",\"cs.CV\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false}