{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T05:47:09Z","timestamp":1777873629137,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":61,"publisher":"ACM","funder":[{"DOI":"10.13039\/501100006374","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100006374","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100006374","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100006374","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100006374","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100006374","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,8,3]]},"DOI":"10.1145\/3711896.3736878","type":"proceedings-article","created":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T13:30:13Z","timestamp":1754055013000},"page":"591-602","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":5,"title":["CityGPT: Empowering Urban Spatial Cognition of Large Language Models"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3279-7117","authenticated-orcid":false,"given":"Jie","family":"Feng","sequence":"first","affiliation":[{"name":"Department of Electronic Engineering, BNRist, Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-9729-9700","authenticated-orcid":false,"given":"Tianhui","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Electronic and Information Engineering, Beijing Jiaotong University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-7197-4367","authenticated-orcid":false,"given":"Yuwei","family":"Du","sequence":"additional","affiliation":[{"name":"Department of Electronic Engineering, BNRist, Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-0837-7498","authenticated-orcid":false,"given":"Siqi","family":"Guo","sequence":"additional","affiliation":[{"name":"Department of Electronic Engineering, Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0442-7071","authenticated-orcid":false,"given":"Yuming","family":"Lin","sequence":"additional","affiliation":[{"name":"Department of Urban Planning, Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5617-1659","authenticated-orcid":false,"given":"Yong","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Electronic Engineering, BNRist, Tsinghua University, Beijing, China"}]}],"member":"320","published-online":{"date-parts":[[2025,8,3]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Josh Achiam Steven Adler Sandhini Agarwal and et al. 2023. Gpt-4 technical report. arXiv preprint arXiv:2303.08774(2023)."},{"key":"e_1_3_2_1_2_1","volume-title":"Llemma: An open language model for mathematics. arXiv preprint arXiv:2310.10631(2023).","author":"Azerbayev Zhangir","year":"2023","unstructured":"Zhangir Azerbayev, Hailey Schoelkopf, Keiran Paster, and et al., 2023. Llemma: An open language model for mathematics. arXiv preprint arXiv:2310.10631(2023)."},{"key":"e_1_3_2_1_3_1","unstructured":"Jinze Bai Shuai Bai Yunfei Chu and et al. 2023. Qwen Technical Report. arXiv preprint arXiv:2309.16609(2023)."},{"key":"e_1_3_2_1_4_1","volume-title":"LAMP: A Language Model on the Map. arXiv preprint arXiv:2403.09059(2024).","author":"Balsebre Pasquale","year":"2024","unstructured":"Pasquale Balsebre, Weiming Huang, and Gao Cong. 2024. LAMP: A Language Model on the Map. arXiv preprint arXiv:2403.09059(2024)."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3589132.3625625"},{"key":"e_1_3_2_1_6_1","unstructured":"Tom Brown Benjamin Mann Nick Ryder Melanie Subbiah Jared D Kaplan Prafulla Dhariwal Arvind Neelakantan Pranav Shyam Girish Sastry Amanda Askell et al. 2020. Language models are few-shot learners. Advances in neural information processing systems Vol. 33 (2020) 1877-1901."},{"key":"e_1_3_2_1_7_1","unstructured":"Karl Cobbe Vineet Kosaraju Mohammad Bavarian Mark Chen Heewoo Jun Lukasz Kaiser Matthias Plappert Jerry Tworek Jacob Hilton Reiichiro Nakano et al. 2021. Training verifiers to solve math word problems. arXiv preprint arXiv:2110.14168(2021)."},{"key":"e_1_3_2_1_8_1","unstructured":"OpenCompass Contributors. 2023. OpenCompass: A Universal Evaluation Platform for Foundation Models. https:\/\/github.com\/open-compass\/opencompass."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-022-04486-7"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3616855.3635772"},{"key":"e_1_3_2_1_11_1","unstructured":"Jingtao Ding Yunke Zhang Yu Shang Yuheng Zhang Zefang Zong Jie Feng Yuan Yuan Hongyuan Su Nian Li Nicholas Sukiennik et al. 2024. Understanding World or Predicting Future? A Comprehensive Survey of World Models. arXiv preprint arXiv:2411.14499(2024)."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"crossref","unstructured":"Ning Ding Yulin Chen Bokai Xu Yujia Qin Zhi Zheng Shengding Hu Zhiyuan Liu Maosong Sun and Bowen Zhou. 2023. Enhancing chat language models by scaling high-quality instructional conversations. arXiv:2305.14233(2023).","DOI":"10.18653\/v1\/2023.emnlp-main.183"},{"key":"e_1_3_2_1_13_1","unstructured":"Guanting Dong Hongyi Yuan Keming Lu Chengpeng Li Mingfeng Xue Dayiheng Liu Wei Wang Zheng Yuan Chang Zhou and Jingren Zhou. 2023. How abilities in large language models are affected by supervised fine-tuning data composition. arXiv preprint arXiv:2310.05492(2023)."},{"key":"e_1_3_2_1_14_1","unstructured":"Abhimanyu Dubey Abhinav Jauhri et al. 2024. The Llama 3 Herd of Models. ArXiv Vol. abs\/2407.21783 (2024). https:\/\/api.semanticscholar.org\/CorpusID:271571434"},{"key":"e_1_3_2_1_15_1","volume-title":"Joshua B Julian, and Hugo J Spiers.","author":"Epstein Russell A","year":"2017","unstructured":"Russell A Epstein, Eva Zita Patai, Joshua B Julian, and Hugo J Spiers. 2017. The cognitive map in humans: spatial navigation and beyond. Nature neuroscience, Vol. 20, 11 (2017), 1504-1513."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41583-022-00655-9"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"crossref","unstructured":"Jie Feng Yuwei Du Jie Zhao and Yong Li. 2025a. AgentMove: A large language model based agentic framework for zero-shot next location prediction. In NAACL.","DOI":"10.18653\/v1\/2025.naacl-long.61"},{"key":"e_1_3_2_1_18_1","unstructured":"Jie Feng Jinwei Zeng Qingyue Long Hongyi Chen Jie Zhao Yanxin Xi Zhilun Zhou Yuan Yuan Shengyuan Wang Qingbin Zeng et al. 2025b. A Survey of Large Language Model-Powered Spatial Intelligence Across Scales: Advances in Embodied Agents Smart Cities and Earth Science. arXiv:2504.09848(2025)."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"crossref","unstructured":"Nathan Godey \u00c9ric de la Clergerie and Beno^it Sagot. 2024. On the Scaling Laws of Geographical Representation in Language Models. arXiv:2402.19406(2024).","DOI":"10.63317\/5dk5bqrxymap"},{"key":"e_1_3_2_1_20_1","volume-title":"Accelerate: Training and inference at scale made simple, efficient and adaptable. https:\/\/github.com\/huggingface\/accelerate.","author":"Gugger Sylvain","year":"2022","unstructured":"Sylvain Gugger, Lysandre Debut, Thomas Wolf, Philipp Schmid, Zachary Mueller, Sourab Mangrulkar, Marc Sun, and Benjamin Bossan. 2022. Accelerate: Training and inference at scale made simple, efficient and adaptable. https:\/\/github.com\/huggingface\/accelerate."},{"key":"e_1_3_2_1_21_1","unstructured":"Wes Gurnee and Max Tegmark. 2023. Language models represent space and time. arXiv preprint arXiv:2310.02207(2023)."},{"key":"e_1_3_2_1_22_1","unstructured":"Dan Hendrycks Collin Burns Steven Basart Andy Zou Mantas Mazeika Dawn Song and Jacob Steinhardt. 2020. Measuring massive multitask language understanding. arXiv preprint arXiv:2009.03300(2020)."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539021"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3600006.3613165"},{"key":"e_1_3_2_1_25_1","volume-title":"Platypus: Quick, cheap, and powerful refinement of llms. arXiv preprint arXiv:2308.07317(2023).","author":"Lee Ariel N","year":"2023","unstructured":"Ariel N Lee, Cole J Hunter, and Nataniel Ruiz. 2023. Platypus: Quick, cheap, and powerful refinement of llms. arXiv preprint arXiv:2308.07317(2023)."},{"key":"e_1_3_2_1_26_1","volume-title":"Geoglue: A geographic language understanding evaluation benchmark. arXiv preprint arXiv:2305.06545(2023).","author":"Li Dongyang","year":"2023","unstructured":"Dongyang Li, Ruixue Ding, Qiang Zhang, Zheng Li, Boli Chen, Pengjun Xie, Yao Xu, Xin Li, Ning Guo, Fei Huang, et al., 2023a. Geoglue: A geographic language understanding evaluation benchmark. arXiv preprint arXiv:2305.06545(2023)."},{"key":"e_1_3_2_1_27_1","first-page":"31199","article-title":"Pre-trained language models for interactive decision-making","volume":"35","author":"Li Shuang","year":"2022","unstructured":"Shuang Li, Xavier Puig, Chris Paxton, Yilun Du, Clinton Wang, Linxi Fan, Tao Chen, De-An Huang, Ekin Aky\u00fcrek, Anima Anandkumar, et al., 2022b. Pre-trained language models for interactive decision-making. Advances in Neural Information Processing Systems, Vol. 35 (2022), 31199-31212.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_28_1","unstructured":"Zekun Li Jina Kim Yao-Yi Chiang and Muhao Chen. 2022a. SpaBERT: A Pretrained Language Model from Geographic Data for Geo-Entity Representation. arXiv preprint arXiv:2210.12213(2022)."},{"key":"e_1_3_2_1_29_1","volume-title":"Geolm: Empowering language models for geospatially grounded language understanding. arXiv preprint arXiv:2310.14478(2023).","author":"Li Zekun","year":"2023","unstructured":"Zekun Li, Wenxuan Zhou, Yao-Yi Chiang, and Muhao Chen. 2023b. Geolm: Empowering language models for geospatially grounded language understanding. arXiv preprint arXiv:2310.14478(2023)."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3588577"},{"key":"e_1_3_2_1_31_1","volume-title":"The image of the city","author":"Lynch Kevin","unstructured":"Kevin Lynch. 1964. The image of the city. MIT press."},{"key":"e_1_3_2_1_32_1","unstructured":"Gengchen Mai Weiming Huang Jin Sun Suhang Song Deepak Mishra Ninghao Liu Song Gao Tianming Liu Gao Cong Yingjie Hu et al. 2023. On the opportunities and challenges of foundation models for geospatial artificial intelligence. arXiv preprint arXiv:2304.06798(2023)."},{"key":"e_1_3_2_1_33_1","series-title":"AGILE: GIScience series","volume-title":"Geographic question answering: challenges, uniqueness, classification, and future directions","author":"Mai Gengchen","year":"2021","unstructured":"Gengchen Mai, Krzysztof Janowicz, Rui Zhu, Ling Cai, and Ni Lao. 2021. Geographic question answering: challenges, uniqueness, classification, and future directions. AGILE: GIScience series, Vol. 2 (2021), 8."},{"key":"e_1_3_2_1_34_1","unstructured":"Rohin Manvi Samar Khanna Marshall Burke David Lobell and Stefano Ermon. 2024. Large language models are geographically biased. arXiv preprint arXiv:2402.02680(2024)."},{"key":"e_1_3_2_1_35_1","volume-title":"Geollm: Extracting geospatial knowledge from large language models. arXiv preprint arXiv:2310.06213(2023).","author":"Manvi Rohin","year":"2023","unstructured":"Rohin Manvi, Samar Khanna, Gengchen Mai, Marshall Burke, David Lobell, and Stefano Ermon. 2023. Geollm: Extracting geospatial knowledge from large language models. arXiv preprint arXiv:2310.06213(2023)."},{"key":"e_1_3_2_1_36_1","unstructured":"Meta. 2024. Introducing Meta Llama 3: The most capable openly available LLM to date. https:\/\/ai.meta.com\/blog\/meta-llama-3\/."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"crossref","unstructured":"Roshanak Mirzaee and Parisa Kordjamshidi. 2022. Transfer learning with synthetic corpora for spatial role labeling and reasoning. arXiv preprint arXiv:2210.16952(2022).","DOI":"10.18653\/v1\/2022.emnlp-main.413"},{"key":"e_1_3_2_1_38_1","volume-title":"Hiteshi Sharma, Nebojsa Jojic, Hamid Palangi, Robert Ness, and Jonathan Larson.","author":"Momennejad Ida","year":"2024","unstructured":"Ida Momennejad, Hosein Hasanbeig, Felipe Vieira Frujeri, Hiteshi Sharma, Nebojsa Jojic, Hamid Palangi, Robert Ness, and Jonathan Larson. 2024. Evaluating cognitive maps and planning in large language models with CogEval. Advances in Neural Information Processing Systems, Vol. 36 (2024)."},{"key":"e_1_3_2_1_39_1","unstructured":"OpenAI. 2022. Introducing ChatGPT. https:\/\/openai.com\/blog\/chatgpt\/."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3281354.3281362"},{"key":"e_1_3_2_1_41_1","unstructured":"Jonathan Roberts Timo L\u00fcddecke Sowmen Das Kai Han and Samuel Albanie. 2023. GPT4GEO: How a Language Model Sees the World's Geography. arXiv preprint arXiv:2306.00020(2023)."},{"key":"e_1_3_2_1_42_1","volume-title":"Beyond Imitation: Generating Human Mobility from Context-aware Reasoning with Large Language Models. arXiv preprint arXiv:2402.09836(2024).","author":"Shao Chenyang","year":"2024","unstructured":"Chenyang Shao, Fengli Xu, Bingbing Fan, Jingtao Ding, Yuan Yuan, Meng Wang, and Yong Li. 2024. Beyond Imitation: Generating Human Mobility from Context-aware Reasoning with Large Language Models. arXiv preprint arXiv:2402.09836(2024)."},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i10.21383"},{"key":"e_1_3_2_1_44_1","first-page":"172","volume-title":"Nature","volume":"620","author":"Singhal Karan","year":"2023","unstructured":"Karan Singhal, Shekoofeh Azizi, Tao Tu, S Sara Mahdavi, Jason Wei, Hyung Won Chung, Nathan Scales, Ajay Tanwani, Heather Cole-Lewis, Stephen Pfohl, et al., 2023. Large language models encode clinical knowledge. Nature, Vol. 620, 7972 (2023), 172-180."},{"key":"e_1_3_2_1_45_1","volume-title":"Aakanksha Chowdhery, Quoc V Le, Ed H Chi, Denny Zhou, et al.","author":"Suzgun Mirac","year":"2022","unstructured":"Mirac Suzgun, Nathan Scales, Nathanael Sch\u00e4rli, Sebastian Gehrmann, Yi Tay, Hyung Won Chung, Aakanksha Chowdhery, Quoc V Le, Ed H Chi, Denny Zhou, et al., 2022. Challenging big-bench tasks and whether chain-of-thought can solve them. arXiv preprint arXiv:2210.09261(2022)."},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.34740\/KAGGLE\/M\/3301"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"crossref","unstructured":"Mistral AI team. 2025. Mistral Small 3. https:\/\/mistral.ai\/news\/mistral-small-3\/.","DOI":"10.5840\/mr2025312"},{"key":"e_1_3_2_1_48_1","unstructured":"Qwen Team. 2024b. Qwen2.5: A Party of Foundation Models. https:\/\/qwenlm.github.io\/blog\/qwen2.5\/"},{"key":"e_1_3_2_1_49_1","unstructured":"Hugo Touvron Louis Martin Kevin Stone Peter Albert Amjad Almahairi Yasmine Babaei Nikolay Bashlykov Soumya Batra Prajjwal Bhargava Shruti Bhosale et al. 2023. Llama 2: Open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288(2023)."},{"key":"e_1_3_2_1_50_1","unstructured":"Xinglei Wang Meng Fang Zichao Zeng and Tao Cheng. 2023a. Where would i go next? large language models as human mobility predictors. arXiv preprint arXiv:2308.15197(2023)."},{"key":"e_1_3_2_1_51_1","unstructured":"Xi Wang Xianyao Ling Tom Zhang Xuecao Li Shaolan Wang Zhixing Li Liang Zhang and Peng Gong. 2023b. Optimizing and Fine-tuning Large Language Model for Urban Renewal. arXiv preprint arXiv:2311.15490(2023)."},{"key":"e_1_3_2_1_52_1","unstructured":"Jason Wei Yi Tay Rishi Bommasani Colin Raffel Barret Zoph Sebastian Borgeaud Dani Yogatama Maarten Bosma Denny Zhou Donald Metzler et al. 2022. Emergent abilities of large language models. arXiv preprint arXiv:2206.07682(2022)."},{"key":"e_1_3_2_1_53_1","volume-title":"Bloomberggpt: A large language model for finance. arXiv preprint arXiv:2303.17564(2023).","author":"Wu Shijie","year":"2023","unstructured":"Shijie Wu, Ozan Irsoy, Steven Lu, Vadim Dabravolski, Mark Dredze, Sebastian Gehrmann, Prabhanjan Kambadur, David Rosenberg, and Gideon Mann. 2023. Bloomberggpt: A large language model for finance. arXiv preprint arXiv:2303.17564(2023)."},{"key":"e_1_3_2_1_54_1","volume-title":"Language models meet world models: Embodied experiences enhance language models. Advances in neural information processing systems","author":"Xiang Jiannan","year":"2024","unstructured":"Jiannan Xiang, Tianhua Tao, Yi Gu, Tianmin Shu, Zirui Wang, Zichao Yang, and Zhiting Hu. 2024. Language models meet world models: Embodied experiences enhance language models. Advances in neural information processing systems, Vol. 36 (2024)."},{"key":"e_1_3_2_1_55_1","unstructured":"Derong Xu Wei Chen Wenjun Peng Chao Zhang Tong Xu Xiangyu Zhao Xian Wu Yefeng Zheng and Enhong Chen. 2023. Large language models for generative information extraction: A survey. arXiv preprint arXiv:2312.17617(2023)."},{"key":"e_1_3_2_1_56_1","unstructured":"Yutaro Yamada Yihan Bao Andrew K Lampinen Jungo Kasai and Ilker Yildirim. 2023. Evaluating Spatial Understanding of Large Language Models. arXiv preprint arXiv:2310.14540(2023)."},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1145\/2339530.2339561"},{"key":"e_1_3_2_1_58_1","volume-title":"Agenttuning: Enabling generalized agent abilities for llms. arXiv preprint arXiv:2310.12823(2023).","author":"Zeng Aohan","year":"2023","unstructured":"Aohan Zeng, Mingdao Liu, Rui Lu, Bowen Wang, Xiao Liu, Yuxiao Dong, and Jie Tang. 2023. Agenttuning: Enabling generalized agent abilities for llms. arXiv preprint arXiv:2310.12823(2023)."},{"key":"e_1_3_2_1_59_1","unstructured":"Aohan Zeng Xiao Liu Zhengxiao Du Zihan Wang Hanyu Lai Ming Ding Zhuoyi Yang Yifan Xu Wendi Zheng Xiao Xia et al. 2022. Glm-130b: An open bilingual pre-trained model. arXiv preprint arXiv:2210.02414(2022)."},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"crossref","unstructured":"Jirong Zha Yuxuan Fan Xiao Yang Chen Gao and Xinlei Chen. 2025. How to Enable LLM with 3D Capacity? A Survey of Spatial Reasoning in LLM. IJCAI(2025).","DOI":"10.24963\/ijcai.2025\/1200"},{"key":"e_1_3_2_1_61_1","unstructured":"Wayne Xin Zhao Kun Zhou Junyi Li Tianyi Tang Xiaolei Wang Yupeng Hou Yingqian Min Beichen Zhang Junjie Zhang Zican Dong et al. 2023. A survey of large language models. arXiv preprint arXiv:2303.18223(2023)."}],"event":{"name":"KDD '25: The 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining","location":"Toronto ON Canada","acronym":"KDD '25","sponsor":["SIGKDD ACM Special Interest Group on Knowledge Discovery in Data","SIGMOD ACM Special Interest Group on Management of Data"]},"container-title":["Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3711896.3736878","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T18:07:29Z","timestamp":1777572449000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3711896.3736878"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,3]]},"references-count":61,"alternative-id":["10.1145\/3711896.3736878","10.1145\/3711896"],"URL":"https:\/\/doi.org\/10.1145\/3711896.3736878","relation":{},"subject":[],"published":{"date-parts":[[2025,8,3]]},"assertion":[{"value":"2025-08-03","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}