Mapping and comparing climate equity policy practices using RAG LLM-based semantic analysis and recommendation systems

Abstract

This study investigates the use of Large Language Models to enhance the policymaking process. We first analyze planning-related job postings to revisit the evolving roles of planners in the era of AI. We then present the Retrieval-Augmented Policy Analysis Framework (RAPAF), implemented using LangChain-native Retrieval-Augmented Generation pipelines with ChatGPT. The framework performs semantic analysis and extracts policy, strategy, and action items related to common themes in climate equity/justice or action plans. Based on these extracted elements and their evaluated presence, we develop a content-based recommendation system to support cross-city policy comparison. The results indicate that, despite growing attention to AI, planning jobs largely retain their traditional domain emphases in transportation, environmental planning, housing, and land use. Communicative responsibilities remain central to planning practice. Climate equity/justice or action plans commonly address transportation, environmental, and energy-related measures aimed at reducing greenhouse gas emissions and predominantly employ affirmative language. The implementation of our content-based recommendation system demonstrates how planners can efficiently identify cities with similar policy themes, highlighting patterns of cross-jurisdictional semantic similarity. The study concludes by envisioning localized and personalized AI-assisted systems designed to support professional planning judgment within urban governance contexts.

Keywords

AI / LLM / RAG / LangChain / Recommendation system / Climate equity plan

References

[1] Aboagye PD, Sharifi A. Urban climate adaptation and mitigation action plans: A critical review. Renewable and Sustainable Energy Reviews, 2024, 189 ArticleID: 113886

[2] Acharya, A., Singh, B., & Onoe, N. (2023). Llm based generation of item-description for recommendation system. 1204–1207.

[3] Adam H, Lin J, Lin J, Keenan H, Wilson A, Ghassemi M. Clinical information extraction with large language models: A case study on organ procurement. American Medical Informatics Association Annual Symposium Proceedings, 2025, 2024: 115-123

[4] Agüero JR, Takayesu E, Novosel D, Masiello R. Grid modernization: Challenges and opportunities. The Electricity Journal, 2017, 30(4): 1-6

[5] APA (2021). AICP code of ethics and professional conduct [WWW Document]. American Planning Association. URL https://www.planning.org/ethics/ethicscode/. Accessed 5.9.26.

[6] Bai Z, Wu Y, Kang X, Kong X, Zhang J. Using LLMs for the multidimensional perception assessment of recreation and leisure spaces: A case study of Hangzhou, China. Computational Urban Science, 2026, 6(1 ArticleID: 9

[7] Bowen GA. Document analysis as a qualitative research method. Qualitative Research Journal, 2009, 9: 27-40

[8] Bowen W. An analytical review of environmental justice research: What do we really know?. Environmental Management, 2002, 29(1): 3-15

[9] Brooks M. Planning theory for practitioners, 2002Routledge

[10] Brynjolfsson, E., Chandar, B., Chen, R. (2025). Canaries in the coal mine? Six facts about the recent employment effects of artificial intelligence. Stanford Digital Economy Lab. https://digitaleconomy.stanford.edu/publications/canaries-in-the-coal-mine/

[11] Buehler R, Hamre A. The multimodal majority? Driving, walking, cycling, and public transportation use among American adults. Transportation, 2015, 42(6): 1081-1101

[12] Caprotti F, Cugurullo F, Cook M, Karvonen A, Marvin S, McGuirk P, Valdez A-M. Why does urban artificial intelligence (AI) matter for urban studies? Developing research directions in urban AI research. Urban Geography, 2024, 45(5): 883-894

[13] Carbonell, J., & Goldstein, J. (1998). The use of MMR, diversity-based reranking for reordering documents and producing summaries. Proceedings of the 21st Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR ’98, 335–336. https://doi.org/10.1145/290941.291025

[14] Chase, H. (2022). LangChain [Python]. https://github.com/langchain-ai/langchain. (Original work published 2022).

[15] Chiu, H., Hachiuma, R., Wang, C.-Y., Smith, S. F., Wang, Y.-C. F., & Chen, M.-H. (2025). V2v-llm: Vehicle-to-vehicle cooperative autonomous driving with multi-modal large language models. arXiv Preprint arXiv:2502.09980.

[16] Choi SJ, Jiao J. Developing a transit desert interactive dashboard: Supervised modeling for forecasting transit deserts. PLoS ONE, 2024, 19(7 ArticleID: e0306782

[17] City of Berkeley. (2009). Climate action plan. https://sustainability.berkeley.edu/sites/default/files/2009_UCB_Climate_Action_Plan.pdf

[18] City of Richmond. (2026). Climate action plan | Richmond, CA - Official Website. https://www.ci.richmond.ca.us/3313/Climate-Action-Plan

[19] City of Las Vegas. (2026). Master plan. https://www.lasvegasnevada.gov/Business/Planning-Zoning/Master-Plan

[20] City of Ann Arbor. (2026). The plan. City of Ann Arbor. https://www.a2gov.org/sustainability-innovations-home/carbon-neutrality-home/the-plan/

[21] City of Chicago. (2026). Home | 2022 Chicago climate action plan. https://www.chicago.gov/content/city/en/sites/climate-action-plan/home.html

[22] Damsø T, Kjær T, Christensen TB. Local climate action plans in climate change mitigation–Examining the case of Denmark. Energy Policy, 2016, 89: 74-83

[23] Davidson, J., Liebald, B., Liu, J., Nandy, P., Van Vleet, T., Gargi, U., Gupta, S., He, Y., Lambert, M., & Livingston, B. (2010). The YouTube video recommendation system. 293–296.

[24] Deetjen TA, Conger JP, Leibowicz BD, Webber ME. Review of climate action plans in 29 major US cities: Comparing current policies to research recommendations. Sustainable Cities and Society, 2018, 41: 711-727

[25] Deng, Z., Fu, X., Li, C., 2025. Automating urban policy extraction: A large language model-based framework for extracting local heat policies from planning documents. Environment and Planning B: Urban Analytics and City Science, 23998083251382381. https://doi.org/10.1177/23998083251382381

[26] Douze, M., Guzhva, A., Deng, C., Johnson, J., Szilvasy, G., Mazaré, P.-E., Lomeli, M., Hosseini, L., & Jégou, H. (2025). The Faiss library (arXiv:2401.08281). arXiv. https://doi.org/10.48550/arXiv.2401.08281

[27] Egger, R., Yu, J. (2022). A topic modeling comparison between LDA, NMF, Top2Vec, and BERTopic to demystify twitter posts. Front Sociol, 7. https://doi.org/10.3389/fsoc.2022.886498

[28] Fainstein SS, DeFilippis J. Readings in planning theory, 2015John Wiley & Sons

[29] Forester J. Planning in the face of power. Journal of the American Planning Association, 1982, 48(1): 67-80

[30] Franco C, Melica G, Palermo V, Bertoldi P. Evidence on local climate policies achieving emission reduction targets by 2030. Urban Climate, 2025, 59 ArticleID: 102242

[31] Fuso Nerini F, Sovacool B, Hughes N, Cozzi L, Cosgrave E, Howells M, Tavoni M, Tomei J, Zerriffi H, Milligan B. Connecting climate action with other Sustainable Development Goals. Nature Sustainability, 2019, 2(8): 674-680

[32] Gupta, A., Basu, D., Ghantasala, R., Qiu, S., & Gadiraju, U. (2022). To trust or not to trust: How a conversational interface affects trust in a decision support system. 3531–3540.

[33] Huang, X., Tu, Z., Ye, X., Goodchild, M. (2026). The role of open-source LLMs in shaping the future of GeoAI. Annals of GIS 1–10. https://doi.org/10.1080/19475683.2026.2630753

[34] Huang L, Yu W, Ma W, Zhong W, Feng Z, Wang H, Chen Q, Peng W, Feng X, Qin B, Liu T. A survey on hallucination in large language models: Principles, taxonomy, challenges, and open questions. ACM Transactions on Information Systems, 2025, 43(2): 42:1-42:55

[35] James T, Andrews G. Levelling the playing field through GenAI: Harnessing artificial intelligence to bridge educational gaps for equity and disadvantaged students. Widening Participation and Lifelong Learning, 2024, 26(3): 250-260

[36] Kalyuzhnaya, A., Mityagin, S., Lutsenko, E., Getmanov, A., Aksenkin, Y., Fatkhiev, K., Fedorin, K., Nikitin, N.O., Chichkova, N., Vorona, V., Boukhanovsky, A. (2025). LLM Agents for Smart City Management: Enhancing Decision Support Through Multi-Agent AI Systems. Smart Cities,8(19). https://doi.org/10.3390/smartcities8010019

[37] Karner A, London J, Rowangould D, Manaugh K. From transportation equity to transportation justice: Within, through, and beyond the state. Journal of Planning Literature, 2020, 35(4): 440-459

[38] Karner A, Niemeier D. Civil rights guidance and equity analysis methods for regional transportation plans: A critical review of literature and practice. Journal of Transport Geography, 2013, 33: 126-134

[39] Karner A, Pereira RH, Farber S. Advances and pitfalls in measuring transportation equity. Transportation, 2025, 52(4): 1399-1427

[40] Kgomo, J., & Song, Z. (2025). AI4Policy: AI-enabled scenario planning for policy-making in the age of AI. Available at SSRN 5710143.

[41] Ki D, Chen Z. From images to insights: ChatGPT and Google Street View for walkability assessments. Transportation Research Part d: Transport and Environment, 2026, 154 ArticleID: 105245

[42] Ki D, Lee H, Park K, Ha J, Lee S. Measuring nuanced walkability: Leveraging ChatGPT’s vision reasoning with multisource spatial data. Computers, Environment and Urban Systems, 2025, 121 ArticleID: 102319

[43] Klingbeil A, Grützner C, Schreck P. Trust and reliance on AI—An experimental study on the extent and costs of overreliance on AI. Computers in Human Behavior, 2024, 160 ArticleID: 108352

[44] Korini, K., Bizer, C. (2025). Evaluating knowledge generation and self-refinement strategies for LLM-based column type annotation. https://doi.org/10.48550/arXiv.2503.02718

[45] Kornblith AE, Singh C, Innes JC, Chang TP, Adelgais KM, Holsti M, Kim J, McClain B, Nishijima DK, Rodgers S. Analyzing patient perspectives with large language models: A cross-sectional study of sentiment and thematic classification on exception from informed consent. Scientific Reports, 2025, 15(1): 6179

[46] Lai, S., Xu, Z., Zhang, W., Liu, H., & Xiong, H. (2025). Llmlight: Large language models as traffic signal control agents. 2335–2346.

[47] Lee, M. K., Kusbit, D., Kahng, A., Kim, J. T., Yuan, X., Chan, A., See, D., Noothigattu, R., Lee, S., & Psomas, A. (2019). WeBuildAI: Participatory framework for algorithmic governance. Proceedings of the ACM on Human-Computer Interaction, 3(CSCW), 1–35.

[48] Lewis, P., Perez, E., Piktus, A., Petroni, F., Karpukhin, V., Goyal, N., Küttler, H., Lewis, M., Yih, W., Rocktäschel, T., Riedel, S., & Kiela, D. (2020). Retrieval-augmented generation for knowledge-intensive NLP tasks. Advances in Neural Information Processing Systems, 33, 9459–9474. https://proceedings.neurips.cc/paper/2020/hash/6b493230205f780e1bc26945df7481e5-Abstract.html

[49] Li, Z., Xu, J., Wang, S., Wu, Y., Li, H. (2024). Streetviewllm: Extracting geographic information using a chain-of-thought multimodal large language model. https://doi.org/10.2139/ssrn.5041619

[50] Li Z, Su Y, Biljecki F, Zhao W. BuildingMultiView: Powering multi-scale building characterization with large language models and multi-perspective imagery. International Journal of Applied Earth Observation and Geoinformation, 2026, 146 ArticleID: 105034

[51] Liu R, Zhe T, Peng Z-R, Catbas N, Ye X, Wang D, Fu Y. Urban planning in the age of agentic AI: Emerging paradigms and prospects. ACM SIGKDD Explorations Newsletter, 2025, 27(2): 35-42

[52] Loh CG, Kim R. Are we planning for equity? Equity goals and recommendations in local comprehensive plans. Journal of the American Planning Association, 2021, 87(2): 181-196

[53] Long Beach. (2026). Long beach climate action plan. https://longbeach.gov/link/b53cfa0709214315aee6fc672aaecc32.aspx?epslanguage=en

[54] Mai G, Huang W, Sun J, Song S, Mishra D, Liu N, Gao S, Liu T, Cong G, Hu Y, Cundy C, Li Z, Zhu R, Lao N. On the opportunities and challenges of foundation models for GeoAI (vision paper). ACM Transactions on Spatial Algorithms and Systems, 2024, 10: 1-46

[55] Mohawesh R, Ottom MA, Salameh HB. A data-driven risk assessment of cybersecurity challenges posed by generative AI. Decision Analytics Journal, 2025, 15 ArticleID: 100580

[56] Nazari-Heris M, Loni A, Asadi S, Mohammadi-ivatloo B. Toward social equity access and mobile charging stations for electric vehicles: A case study in Los Angeles. Applied Energy, 2022, 311 ArticleID: 118704

[57] Noy S, Zhang W. Experimental evidence on the productivity effects of generative artificial intelligence. Science, 2023, 381: 187-192

[58] Peeperkorn, M., Kouwenhoven, T., Brown, D., & Jordanous, A. (2024). Is temperature the creativity parameter of large language models? arXiv Preprint. arXiv:2405.00492.

[59] Pehnt M. Dynamic life cycle assessment (LCA) of renewable energy technologies. Renewable Energy, 2006, 31(1): 55-71

[60] Ramjee, P., Chhokar, M., Sachdeva, B., Meena, M., Abdullah, H., Vashistha, A., Nagar, R., & Jain, M. (2025). ASHABot: An LLM-powered chatbot to support the informational needs of community health workers. 1–22.

[61] Resnik DB. Environmental justice and climate change policies. Bioethics, 2022, 36(7): 735-741

[62] Sager T. Communicative planning. The Routledge handbook of planning theory, 2017Routledge93104

[63] Schlosberg D, Collins LB. From environmental to climate justice: Climate change and the discourse of environmental justice. Wiley Interdisciplinary Reviews: Climate Change, 2014, 5(3): 359-374

[64] Seddone, G. (2025). LLMs and the increasing role of the humanities in the digital age. AI & SOCIETY. https://doi.org/10.1007/s00146-025-02778-w

[65] Seneviratne, S. I., Zhang, X., Adnan, M., Badi, W., Dereczynski, C., Luca, A. D., Ghosh, S., Iskandar, I., Kossin, J., & Lewis, S. (2021). Weather and climate extreme events in a changing climate.

[66] Shin DD. Algorithms, humans, and interactions: How do algorithms interact with people? Designing meaningful AI experiences, 2023Taylor & Francis

[67] Shipan CR, Volden C. Policy diffusion: Seven lessons for scholars and practitioners. Public Administration Review, 2012, 72: 788-796

[68] Stewart-Evans, J., Wilson, E., Langley, T., Prayle, A., Hands, A., Exley, K., Leonardi-Bee, J. (2025). Expediting data extraction using a large language model (LLM) and scoping review protocol: a methodological study within a complex scoping review. https://doi.org/10.48550/arXiv.2507.06623

[69] Stone B, Vargo J, Habeeb D. Managing climate change in cities: Will climate action plans work?. Landscape and Urban Planning, 2012, 107(3): 263-271

[70] Suh, S., Chen, M., Min, B., Li, T. J.-J., & Xia, H. (2023). Structured generation and exploration of design space with large language models for human-ai co-creation. arXiv Preprint arXiv:2310.12953, 3.

[71] Tarkoma, S., Morabito, R., & Sauvola, J. (2023). AI-native interconnect framework for integration of large language model technologies in 6G systems. arXiv Preprint arXiv:2311.05842.

[72] Temenos C, McCann E. Geographies of policy mobilities. Geography Compass, 2013, 7(5): 344-357

[73] Tiwari A. A proposal to localising urban AI: A conceptual shift from generalist LLMs to task-specific SLMs. Computational Urban Science, 2026, 6(1): 11

[74] Trenberth KE, Fasullo JT, Shepherd TG. Attribution of climate extreme events. Nature Climate Change, 2015, 5(8): 725-730

[75] UN Environment. (2022). The climate emergency. https://www.unep.org/climate-emergency

[76] Verma, K., & Yadav, S. (2025). Collaborating with generative AI: A review of models, applications and challenges. AI & SOCIETY. https://doi.org/10.1007/s00146-025-02805-w

[77] Waddell P. UrbanSim: Modeling urban development for land use, transportation, and environmental planning. Journal of the American Planning Association, 2002, 68(3): 297-314

[78] Wei, F., Keeling, R., Huber-Fliflet, N., Zhang, J., Dabrowski, A., Yang, J., Mao, Q., & Qin, H. (2023). Empirical study of llm fine-tuning for text classification in legal document review. 2786–2792.

[79] Williams L, Anthi E, Arman L, Burnap P. Topic modelling: Going beyond token outputs. Big Data and Cognitive Computing, 2024, 8 ArticleID: 44

[80] Wu S. A systematic review of climate policies in China: Evolution, effectiveness, and challenges. Environmental Impact Assessment Review, 2023, 99 ArticleID: 107030

[81] Xu H, Omitaomu F, Sabri S, Zlatanova S, Li X, Song Y. Leveraging generative AI for urban digital twins: A scoping review on the autonomous generation of urban data, scenarios, designs, and 3D city models for smart city advancement. Urban Informatics, 2024, 3(1): 29

[82] Ye X, Gong W, Yang Y, Zou L, Tu Z, Huang X, Li Z, Ning H, Wu L. Towards agentic urban digital twins (AUDiTs): Advancing new urban science through human-AI co-learning agents. Urban Info, 2026, 5: 9

[83] Yu, A., Weile, J., Courtot, M. (2026). Benchmarking LLM-based Information Extraction Tools for Medical Documents. medRxiv 2026–01.

[84] Zapata MA, Bates LK. Equity planning revisited. Journal of Planning Education and Research, 2015, 35(3): 245-248

[85] Zhang, Z., Liu, S., Liu, Z., Zhong, R., Cai, Q., Zhao, X., Zhang, C., Liu, Q., & Jiang, P. (2025). Llm-powered user simulator for recommender system. 39(12), 13339–13347.

[86] Zhao, S., Huang, Y., Song, J., Wang, Z., Wan, C., & Ma, L. (2024). Towards understanding retrieval accuracy and prompt quality in rag systems. arXiv Preprint arXiv:2411.19463.

[87] Zheng, Y., Xu, F., Lin, Y., Santi, P., Ratti, C., Wang, Q.R., Li, Y. (2025). Urban planning in the era of large language models. Nature Computational Science,5, 727–736. https://doi.org/10.1038/s43588-025-00846-1

RIGHTS & PERMISSIONS

The Author(s)