---
title: "MONETA — paper by Yüksel et al. (2026) — summary and ideas"
description: "The authors present MONETA, which they describe as the first multimodal benchmark for industry classification. 43 references."
authors: ["Arda Yüksel", "Gabriel Thiem", "Susanne Walter", "Patrick Felka", "Gabriela Alves Werb", "Ivan Habernal"]
year: 2026
venue: "Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)"
source: "https://aclanthology.org/2026.acl-long.674/"
doi: "10.18653/v1/2026.acl-long.674"
licence: "CC BY 4.0 (ACL Anthology)"
licence_url: "https://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/yuksel-2026-moneta-multimodal-industry-classification-through/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/yuksel-2026-moneta-multimodal-industry-classification-through/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2026](https://md.research.elamur.ai/free/en/papers/2026/page/42/) / MONETA: Multimodal Industry Classification through Geographic Information with Multi Agent Systems

# MONETA: Multimodal Industry Classification through Geographic Information with Multi Agent Systems

**Authors:** Arda Yüksel, Gabriel Thiem, Susanne Walter, Patrick Felka, Gabriela Alves Werb and [Ivan Habernal](https://md.research.elamur.ai/free/en/authors/ivan-habernal/) · **Year:** 2026 · **Venue:** [Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)](https://md.research.elamur.ai/free/en/venues/acl/) ([ACL 2026](https://md.research.elamur.ai/free/en/venues/acl/2026/)) · **Publisher:** [Association for Computational Linguistics](https://md.research.elamur.ai/free/en/publishers/association-for-computational-linguistics/) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2026.acl-long.674/) · [PDF](https://aclanthology.org/2026.acl-long.674.pdf) · [DOI 10.18653/v1/2026.acl-long.674](https://doi.org/10.18653/v1/2026.acl-long.674) · [OpenAlex](https://openalex.org/W7166867875)

**Citations:** 0 citations (OpenAlex, 2026-10-14)

## Summary
Business registers have to assign each company its main economic activity. Experts usually do this by hand, which is slow. Existing automatic classifiers have two weaknesses. They depend on text, which new or small firms often lack. They are also fine-tuned to one classification scheme, so they need retraining whenever the scheme is revised.

The authors present MONETA, which they describe as the first multimodal benchmark for industry classification. It covers 1,000 European businesses labelled with 20 NACE sections. Each entry pairs OpenStreetMap renderings and satellite imagery with at least one text source: a website, Wikipedia or Wikidata. To build the dataset, they created a new NACE-to-OSM tag mapping with LLM assistance and manual checking.

They compare two training-free pipelines:
- a zero-shot MLLM classifier;
- a multi-turn, multi-agent design in which each source has its own agent and a decision agent combines their clues.

They also propose a keyword-based way to evaluate the intermediate agents. Accuracy reaches 62.10% with open MLLMs and 74.10% with closed ones. Multi-turn processing, context enrichment and explanations add up to 22.80%. This matters for geospatial finance, for example in climate-risk assessment of company assets.

## Key points
- **Dataset:** 1,000 businesses across 20 NACE sections, with two visual sources (OSM, satellite) and three possible text sources. The NACE-to-OSM mapping is released alongside the data.
- **Source effectiveness:** Text clues track the ground truth more closely than geospatial ones. Websites can push predictions toward NACE Section G (trade), while satellite images sometimes rescue cases with little text.
- **Text-only validation:** Qwen 2.5 was tested on ExioNAICS and Company Websites. With LoRA it scored 89.74% on Company Websites, beating the 88.23% reported by Jagrič and Herman (2024).
- **Cost of fine-tuning:** Fine-tuned models lost more than 35% relative to zero-shot inference when evaluated on a different task. Prompting adapts more easily, for instance to NACE Rev. 2.1.
- **Licensing:** Code is released under Apache 2.0 and annotations under CC BY-SA 4.0. ESRI satellite tiles are not redistributed; a retrieval script is provided instead.

*Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.*

## Institutions

- [Technische Universität Darmstadt](https://md.research.elamur.ai/free/en/universities/technische-universitat-darmstadt/) — University, Darmstadt, Germany · 114 works · 36,326 citations
- [Ruhr University Bochum](https://md.research.elamur.ai/free/en/universities/ruhr-university-bochum/) — University, Bochum, Germany · 27 works · 1,189 citations

Also on the byline: [Frankfurt University of Applied Sciences](https://ror.org/02r625m11) · [Deutsche Bundesbank](https://ror.org/03jvfq589).

📚 Shelves (4): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 18,614 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 17,965 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 17,450 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 17,296 works

🧭 Topics (1): [🖼️ Vision & language](https://md.research.elamur.ai/free/en/topics/multimodal/) · 811 works

## Cite

Cite as: Arda Yüksel, Gabriel Thiem, Susanne Walter, Patrick Felka, Gabriela Alves Werb and Ivan Habernal. 2026. MONETA: Multimodal Industry Classification through Geographic Information with Multi Agent Systems. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers).

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@inproceedings{yuksel2026moneta,
  title = {{MONETA: Multimodal Industry Classification through Geographic Information with Multi Agent Systems}},
  author = {Arda Yüksel, Gabriel Thiem, Susanne Walter, Patrick Felka, Gabriela Alves Werb and Ivan Habernal},
  booktitle = {Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
  year = {2026},
  doi = {10.18653/v1/2026.acl-long.674},
  url = {https://doi.org/10.18653/v1/2026.acl-long.674}
}
```

- [← previous MonCulture-Eval: A Hierarchical Benchmark for Evaluating Mongolian Cultural Capabilities of Large Language Models across Scripts and Regions](https://md.research.elamur.ai/free/en/papers/minggad-2026-monculture-eval-hierarchical-benchmark-evaluating/)
- [next → Moneyball with LLMs: Analyzing Tabular Summarization in Sports Narratives](https://md.research.elamur.ai/free/en/papers/upadhyay-2026-moneyball-llms-analyzing-tabular-summarization/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/42/)

## References

43 references, 9 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Classification (ISIC) Code. In 2022 IEEE International Conference on Big Data (Big Data), pages 3472–3477. [find](https://scholar.google.com/scholar?q=Classification+%28ISIC%29+Code%2E+In+2022+IEEE+International+Conference+on+Big+Data+%28Big+Data%29%2C+pages+3472%E2%80%933477%2E)
2. Wei Chen, Xixuan Hao, Yuankai Wu, and Yuxuan Liang. 2024a. Terra: A multimodal spatio-temporal dataset spanning the earth. In Advances in Neural Information Processing Systems, volume 37, pages 66329– 66356. Curran Associates, Inc. [find](https://scholar.google.com/scholar?q=Wei+Chen%2C+Xixuan+Hao%2C+Yuankai+Wu%2C+and+Yuxuan+Liang%2E+2024a%2E+Terra%3A+A+multimodal+spatio%2Dtemporal+dataset+spanning+the+earth%2E+In+Advances+in+Neural+Information+Processing+Systems%2C+volume+37%2C+pages+66329%E2%80%93)
3. Yuzhou Chen, Jiue-An Yang, Hugo Kyo Lee, Calvin Tribby, Tarik Benmarhnia, Marta Jankowska, and Yulia R. Gel. 2025. Fusing Multimodality of Large Language Models and Satellite Imagery via Simplicial Contrastive Learning for Latent Urban Feature Identification and Environmental Application. In ICASSP… [find](https://scholar.google.com/scholar?q=Yuzhou+Chen%2C+Jiue%2DAn+Yang%2C+Hugo+Kyo+Lee%2C+Calvin+Tribby%2C+Tarik+Benmarhnia%2C+Marta+Jankowska%2C+and+Yulia+R%2E+Gel%2E+2025%2E+Fusing+Multimodality+of+Large+Language+Models+and+Satellite+Imagery+via+Simplicial+Co)
4. Zhe Chen, Weiyun Wang, Yue Cao, Yangzhou Liu, Zhangwei Gao, Erfei Cui, Jinguo Zhu, Shenglong Ye, Hao Tian, Zhaoyang Liu, and 1 others. 2024b. [Expanding performance boundaries of open-source multimodal models with model, data, and test-time scaling](https://md.research.elamur.ai/free/en/papers/chen-2024-expanding-performance-boundaries-open/). arXiv preprint arXiv:2412.05271.
5. Carole A Ambler and James E Kristoff. 1998. Introducing the North American industry classification system. Government Information Quarterly, 15(3):263– 273. [find](https://scholar.google.com/scholar?q=Carole+A+Ambler+and+James+E+Kristoff%2E+1998%2E+Introducing+the+North+American+industry+classification+system%2E+Government+Information+Quarterly%2C+15%283%29%3A263%E2%80%93+273%2E)
6. Annalisa Croce, Laura Toschi, Elisa Ughetto, and Sara Zanni. 2024. Cleantech and policy framework in Europe: A machine learning approach. Energy Policy, 186:114006. [find](https://scholar.google.com/scholar?q=Annalisa+Croce%2C+Laura+Toschi%2C+Elisa+Ughetto%2C+and+Sara+Zanni%2E+2024%2E+Cleantech+and+policy+framework+in+Europe%3A+A+machine+learning+approach%2E+Energy+Policy%2C+186%3A114006%2E)
7. Matteo Ambrois, Vincenzo Butticè, Federico Cavig-gioli, Giovanni Cerulli, Annalisa Croce, Antonio De Marco, Andrea Giordano, Giuliano Resce, Laura Toschi, Elisa Ughetto, and Antonio Zinilli. 2023. Using machine learning to map the european cleantech sector. EIF Working Paper Series 2023/91, European… [find](https://scholar.google.com/scholar?q=Matteo+Ambrois%2C+Vincenzo+Buttic%C3%A8%2C+Federico+Cavig%2Dgioli%2C+Giovanni+Cerulli%2C+Annalisa+Croce%2C+Antonio+De+Marco%2C+Andrea+Giordano%2C+Giuliano+Resce%2C+Laura+Toschi%2C+Elisa+Ughetto%2C+and+Antonio+Zinilli%2E+2023%2E+Usi)
8. Michael Han Daniel Han and Unsloth team. 2023. Unsloth. [find](https://scholar.google.com/scholar?q=Michael+Han+Daniel+Han+and+Unsloth+team%2E+2023%2E+Unsloth%2E)
9. Madeline Loui Anderson, Miriam Cha, William T. Freeman, J. Taylor Perron, Nathaniel Maidel, and Kerri Cahoy. 2025. Measuring and mitigating hallucinations in vision-language dataset generation for remote sensing. In Workshop on Preparing Good Data for Generative AI: Challenges and Approaches. [find](https://scholar.google.com/scholar?q=Madeline+Loui+Anderson%2C+Miriam+Cha%2C+William+T%2E+Freeman%2C+J%2E+Taylor+Perron%2C+Nathaniel+Maidel%2C+and+Kerri+Cahoy%2E+2025%2E+Measuring+and+mitigating+hallucinations+in+vision%2Dlanguage+dataset+generation+for+rem)
10. Jinze Bai, Shuai Bai, Shusheng Yang, Shijie Wang, Sinan Tan, Peng Wang, Junyang Lin, Chang Zhou, and Jingren Zhou. 2023. [Qwen-vl: A versatile vision-language model for understanding, localization, text reading, and beyond](https://md.research.elamur.ai/free/en/papers/bai-2023-qwen-vl-versatile-vision-language/). arXiv preprint arXiv:2308.12966.
11. Guy Stephane Waffo Dzuyo, Gaël Guibon, Christophe Cerisara, and Luis Belmar-Letelier. 2025. Linking Industry Sectors and Financial Statements: A Hybrid Approach for Company Classification. Proceedings of the AAAI Conference on Artificial Intelligence, 39(16):16444–16452. Number: 16. [find](https://scholar.google.com/scholar?q=Guy+Stephane+Waffo+Dzuyo%2C+Ga%C3%ABl+Guibon%2C+Christophe+Cerisara%2C+and+Luis+Belmar%2DLetelier%2E+2025%2E+Linking+Industry+Sectors+and+Financial+Statements%3A+A+Hybrid+Approach+for+Company+Classification%2E+Proceedings)
12. European Commission, editor. 2008. NACE Rev. 2: statistical classification of economic activities in the European Community. Publications Office, Luxembourg. [find](https://scholar.google.com/scholar?q=European+Commission%2C+editor%2E+2008%2E+NACE+Rev%2E+2%3A+statistical+classification+of+economic+activities+in+the+European+Community%2E+Publications+Office%2C+Luxembourg%2E)
13. Thomas Faria and Tom Seimandi. 2023. Classifying companies in france using machine learning. [find](https://scholar.google.com/scholar?q=Thomas+Faria+and+Tom+Seimandi%2E+2023%2E+Classifying+companies+in+france+using+machine+learning%2E)
14. Gemini 2.5 Team. 2025. [Gemini 2.5: Pushing the frontier with advanced reasoning, multimodality, long context, and next generation agentic capabilities](https://md.research.elamur.ai/free/en/papers/comanici-2025-gemini-2-5-pushing-frontier/). Preprint, arXiv:2507.06261.
15. Shuai Bai, Keqin Chen, Xuejing Liu, Jialin Wang, Wenbin Ge, Sibo Song, Kai Dang, Peng Wang, Shijie Wang, Jun Tang, Humen Zhong, Yuanzhi Zhu, Mingkun Yang, Zhaohai Li, Jianqiang Wan, Pengfei Wang, Wei Ding, Zheren Fu, Yiheng Xu, and 8 others. 2025. [Qwen2.5-vl technical report](https://md.research.elamur.ai/free/en/papers/bai-2025-qwen2-5-vl-technical/). arXiv preprint arXiv:25…
16. Sucharita Gopal and Josh Pitts. 2024. Geospatial Finance: Foundations and Applications, pages 225– 273. Springer Nature Switzerland, Cham. [find](https://scholar.google.com/scholar?q=Sucharita+Gopal+and+Josh+Pitts%2E+2024%2E+Geospatial+Finance%3A+Foundations+and+Applications%2C+pages+225%E2%80%93+273%2E+Springer+Nature+Switzerland%2C+Cham%2E)
17. Hannah Béchara, Ran Zhang, Shuzhou Yuan, and Slava Jankin. 2022. Applying NLP Techniques to Classify Businesses by their International Standard Industrial Edward J Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen. 2022. LoRA: Low-rank adaptation of… — [arXiv:2502.06874](https://arxiv.org/abs/2502.06874) [find](https://scholar.google.com/scholar?q=Hannah+B%C3%A9chara%2C+Ran+Zhang%2C+Shuzhou+Yuan%2C+and+Slava+Jankin%2E+2022%2E+Applying+NLP+Techniques+to+Classify+Businesses+by+their+International+Standard+Industrial+Edward+J+Hu%2C+Yelong+Shen%2C+Phillip+Wallis%2C+Zey)
18. Timotej Jagrič and Aljaž Herman. 2024. AI Model for Industry Classification Based on Website Data. Information, 15(2):89. Number: 2 Publisher: Multidisciplinary Digital Publishing Institute. [find](https://scholar.google.com/scholar?q=Timotej+Jagric%CC%8C+and+Alja%C5%BE+Herman%2E+2024%2E+AI+Model+for+Industry+Classification+Based+on+Website+Data%2E+Information%2C+15%282%29%3A89%2E+Number%3A+2+Publisher%3A+Multidisciplinary+Digital+Publishing+Institute%2E)
19. Pu Jin, Gui-Song Xia, Fan Hu, Qikai Lu, and Liangpei Zhang. 2018. AID++: An Updated Version of AID on Scene Classification. In IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium, pages 4721–4724. ISSN: 2153-7003. [find](https://scholar.google.com/scholar?q=Pu+Jin%2C+Gui%2DSong+Xia%2C+Fan+Hu%2C+Qikai+Lu%2C+and+Liangpei+Zhang%2E+2018%2E+AID%2B%2B%3A+An+Updated+Version+of+AID+on+Scene+Classification%2E+In+IGARSS+2018+%2D+2018+IEEE+International+Geoscience+and+Remote+Sensing+Sympo)
20. Sohail Ahmed Khan, Laurence Dierickx, Jan-Gunnar Furuly, Henrik Brattli Vold, Rano Tahseen, Carl-Gustav Linden, and Duc-Tien Dang-Nguyen. 2025. Debunking war information disorder: A case study in assessing the use of multimedia verification tools. Journal of the Association for Information Science a… [find](https://scholar.google.com/scholar?q=Sohail+Ahmed+Khan%2C+Laurence+Dierickx%2C+Jan%2DGunnar+Furuly%2C+Henrik+Brattli+Vold%2C+Rano+Tahseen%2C+Carl%2DGustav+Linden%2C+and+Duc%2DTien+Dang%2DNguyen%2E+2025%2E+Debunking+war+information+disorder%3A+A+case+study+in+asse)
21. Heidi Kühnemann, Arnout van Delden, and Dick Wind-meijer. 2020. Exploring a knowledge-based approach to predicting nace codes of enterprises based on web page texts. Statistical Journal of the IAOS, 36(3):807– 821. [find](https://scholar.google.com/scholar?q=Heidi+K%C3%BChnemann%2C+Arnout+van+Delden%2C+and+Dick+Wind%2Dmeijer%2E+2020%2E+Exploring+a+knowledge%2Dbased+approach+to+predicting+nace+codes+of+enterprises+based+on+web+page+texts%2E+Statistical+Journal+of+the+IAOS%2C+3)
22. Haifeng Li, Hao Jiang, Xin Gu, Jian Peng, Wenbo Li, Liang Hong, and Chao Tao. 2020. CLRS: Continual Learning Benchmark for Remote Sensing Image Scene Classification. Sensors, 20(4):1226. Number: 4 Publisher: Multidisciplinary Digital Publishing Institute. [find](https://scholar.google.com/scholar?q=Haifeng+Li%2C+Hao+Jiang%2C+Xin+Gu%2C+Jian+Peng%2C+Wenbo+Li%2C+Liang+Hong%2C+and+Chao+Tao%2E+2020%2E+CLRS%3A+Continual+Learning+Benchmark+for+Remote+Sensing+Image+Scene+Classification%2E+Sensors%2C+20%284%29%3A1226%2E+Number%3A+4+Pub)
23. Qiang Li, Mingkun Tan, Xun Zhao, Dan Zhang, Daoan Zhang, Shengzhao Lei, Anderson S. Chu, Lujun Li, and Porawit Kamnoedboon. 2025. How LLMs react to industrial spatio-temporal data? assessing hallucination with a novel traffic incident benchmark dataset. In Proceedings of the 2025 Conference of the N… [find](https://scholar.google.com/scholar?q=Qiang+Li%2C+Mingkun+Tan%2C+Xun+Zhao%2C+Dan+Zhang%2C+Daoan+Zhang%2C+Shengzhao+Lei%2C+Anderson+S%2E+Chu%2C+Lujun+Li%2C+and+Porawit+Kamnoedboon%2E+2025%2E+How+LLMs+react+to+industrial+spatio%2Dtemporal+data%3F+assessing+hallucina)
24. Haotian Liu, Chunyuan Li, Yuheng Li, and Yong Jae Lee. 2023a. [Improved baselines with visual instruction tuning](https://md.research.elamur.ai/free/en/papers/liu-2023-improved-baselines-visual-instruction-tuning/).
25. Haotian Liu, Chunyuan Li, Yuheng Li, Bo Li, Yuanhan Zhang, Sheng Shen, and Yong Jae Lee. 2024. Llava-next: Improved reasoning, ocr, and world knowledge. [find](https://scholar.google.com/scholar?q=Haotian+Liu%2C+Chunyuan+Li%2C+Yuheng+Li%2C+Bo+Li%2C+Yuanhan+Zhang%2C+Sheng+Shen%2C+and+Yong+Jae+Lee%2E+2024%2E+Llava%2Dnext%3A+Improved+reasoning%2C+ocr%2C+and+world+knowledge%2E)
26. Haotian Liu, Chunyuan Li, Qingyang Wu, and Yong Jae Lee. 2023b. [Visual instruction tuning](https://md.research.elamur.ai/free/en/papers/liu-2023-visual-instruction-tuning/).
27. Ivan Malashin, Igor Masich, Vadim Tynchenko, Vladimir Nelyub, Aleksei Borodulin, and Andrei Gantimurov. 2024. Application of Natural Language Processing and Genetic Algorithm to Fine-Tune Hyperparameters of Classifiers for Economic Activities Analysis. Big Data and Cognitive Computing, 8(6):68. Numb… [find](https://scholar.google.com/scholar?q=Ivan+Malashin%2C+Igor+Masich%2C+Vadim+Tynchenko%2C+Vladimir+Nelyub%2C+Aleksei+Borodulin%2C+and+Andrei+Gantimurov%2E+2024%2E+Application+of+Natural+Language+Processing+and+Genetic+Algorithm+to+Fine%2DTune+Hyperparamet)
28. Ali Mansourian and Rachid Oucheikh. 2024. Chat-GeoAI: Enabling Geospatial Analysis for Public through Natural Language, with Large Language Models. ISPRS International Journal of Geo-Information, 13(10):348. [find](https://scholar.google.com/scholar?q=Ali+Mansourian+and+Rachid+Oucheikh%2E+2024%2E+Chat%2DGeoAI%3A+Enabling+Geospatial+Analysis+for+Public+through+Natural+Language%2C+with+Large+Language+Models%2E+ISPRS+International+Journal+of+Geo%2DInformation%2C+13%281)
29. Ethan Mendes, Yang Chen, James Hays, Sauvik Das, Wei Xu, and Alan Ritter. 2024. Granular Privacy Control for Geolocation with Vision Language Models. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 17240–17292, Miami, Florida, USA. Association for Com… [find](https://scholar.google.com/scholar?q=Ethan+Mendes%2C+Yang+Chen%2C+James+Hays%2C+Sauvik+Das%2C+Wei+Xu%2C+and+Alan+Ritter%2E+2024%2E+Granular+Privacy+Control+for+Geolocation+with+Vision+Language+Models%2E+In+Proceedings+of+the+2024+Conference+on+Empirical)
30. Hibiki Nakatani, Hiroki Teranishi, Shohei Higashiyama, Yuya Sawada, Hiroki Ouchi, and Taro Watanabe. 2025. A Text Embedding Model with Contrastive Example Mining for Point-of-Interest Geocoding. In Proceedings of the 31st International Conference on Computational Linguistics, pages 7279–7291, Abu Dh… [find](https://scholar.google.com/scholar?q=Hibiki+Nakatani%2C+Hiroki+Teranishi%2C+Shohei+Higashiyama%2C+Yuya+Sawada%2C+Hiroki+Ouchi%2C+and+Taro+Watanabe%2E+2025%2E+A+Text+Embedding+Model+with+Contrastive+Example+Mining+for+Point%2Dof%2DInterest+Geocoding%2E+In+Pr)
31. Sanaz Saki Norouzi and Pascal Hitzler. 2025. Knowledge-Enhanced Geospatial QA: Integrating Wikidata Fact Verification with LLMs. Proceedings of the AAAI Symposium Series, 5(1):334–339. [find](https://scholar.google.com/scholar?q=Sanaz+Saki+Norouzi+and+Pascal+Hitzler%2E+2025%2E+Knowledge%2DEnhanced+Geospatial+QA%3A+Integrating+Wikidata+Fact+Verification+with+LLMs%2E+Proceedings+of+the+AAAI+Symposium+Series%2C+5%281%29%3A334%E2%80%93339%2E)
32. OpenAI. 2025. Gpt-5. [https://openai.com](https://openai.com). Large language model. [↗](https://openai.com)
33. Maryan Rizinski, Andrej Jankov, Vignesh Sankaradas, Eugene Pinsky, Igor Miskovski, and Dimitar Trajanov. 2023. Company classification using zero-shot learning. arXiv preprint. ArXiv:2305.01028 [cs] version: 2. — [arXiv:2305.01028](https://arxiv.org/abs/2305.01028) [find](https://scholar.google.com/scholar?q=Maryan+Rizinski%2C+Andrej+Jankov%2C+Vignesh+Sankaradas%2C+Eugene+Pinsky%2C+Igor+Miskovski%2C+and+Dimitar+Trajanov%2E+2023%2E+Company+classification+using+zero%2Dshot+learning%2E+arXiv+preprint%2E+ArXiv%3A2305%2E01028+%5Bcs%5D+ve)
34. Mohamad Hakam Shams Eddin and Jürgen Gall. 2024. Identifying spatio-temporal drivers of extreme events. In Advances in Neural Information Processing Systems, volume 37, pages 93714–93766. Curran Associates, Inc. [find](https://scholar.google.com/scholar?q=Mohamad+Hakam+Shams+Eddin+and+J%C3%BCrgen+Gall%2E+2024%2E+Identifying+spatio%2Dtemporal+drivers+of+extreme+events%2E+In+Advances+in+Neural+Information+Processing+Systems%2C+volume+37%2C+pages+93714%E2%80%9393766%2E+Curran+Assoc)
35. Zirui Song, Jingpu Yang, Yuan Huang, Jonathan Tonglet, Zeyu Zhang, Tao Cheng, Meng Fang, Iryna Gurevych, and Xiuying Chen. 2025. Geolocation with Real Human Gameplay Data: A Large-Scale Dataset and Human-Like Reasoning Framework. arXiv preprint. ArXiv:2502.13759 [cs]. — [arXiv:2502.13759](https://arxiv.org/abs/2502.13759) [find](https://scholar.google.com/scholar?q=Zirui+Song%2C+Jingpu+Yang%2C+Yuan+Huang%2C+Jonathan+Tonglet%2C+Zeyu+Zhang%2C+Tao+Cheng%2C+Meng+Fang%2C+Iryna+Gurevych%2C+and+Xiuying+Chen%2E+2025%2E+Geolocation+with+Real+Human+Gameplay+Data%3A+A+Large%2DScale+Dataset+and+Hu)
36. Yuan Tao, Wanzeng Liu, Jun Chen, Jingxiang Gao, Ran Li, Xinpeng Wang, Ye Zhang, Jiaxin Ren, Shunxi Yin, Xiuli Zhu, Tingting Zhao, Xi Zhai, and Yunlu Peng. 2025. A graph-based multimodal data fusion framework for identifying urban functional zone. International Journal of Applied Earth Observation an… [find](https://scholar.google.com/scholar?q=Yuan+Tao%2C+Wanzeng+Liu%2C+Jun+Chen%2C+Jingxiang+Gao%2C+Ran+Li%2C+Xinpeng+Wang%2C+Ye+Zhang%2C+Jiaxin+Ren%2C+Shunxi+Yin%2C+Xiuli+Zhu%2C+Tingting+Zhao%2C+Xi+Zhai%2C+and+Yunlu+Peng%2E+2025%2E+A+graph%2Dbased+multimodal+data+fusion+fr)
37. UN. 2008. International Standard Industrial Classification of All Economic Activities (ISIC), Rev.4. Statistical Papers (Ser. M). United Nations, s.l. [find](https://scholar.google.com/scholar?q=UN%2E+2008%2E+International+Standard+Industrial+Classification+of+All+Economic+Activities+%28ISIC%29%2C+Rev%2E4%2E+Statistical+Papers+%28Ser%2E+M%29%2E+United+Nations%2C+s%2El%2E)
38. Dimitrios Vamvourellis, Máté Tóth, Snigdha Bhagat, Dhruv Desai, Dhagash Mehta, and Stefano Pasquali. 2024. Company similarity using large language models. In 2024 IEEE Symposium on Computational Intelligence for Financial Engineering and Economics (CIFEr), pages 1–9. [find](https://scholar.google.com/scholar?q=Dimitrios+Vamvourellis%2C+M%C3%A1t%C3%A9+T%C3%B3th%2C+Snigdha+Bhagat%2C+Dhruv+Desai%2C+Dhagash+Mehta%2C+and+Stefano+Pasquali%2E+2024%2E+Company+similarity+using+large+language+models%2E+In+2024+IEEE+Symposium+on+Computational+Intel)
39. Peng Wang, Shuai Bai, Sinan Tan, Shijie Wang, Zhihao Fan, Jinze Bai, Keqin Chen, Xuejing Liu, Jialin Wang, Wenbin Ge, Yang Fan, Kai Dang, Mengfei Du, Xuancheng Ren, Rui Men, Dayiheng Liu, Chang Zhou, Jingren Zhou, and Junyang Lin. 2024a. [Qwen2-vl: Enhancing vision-language model’s perception of the…](https://md.research.elamur.ai/free/en/papers/wang-2024-qwen2-vl-enhancing-vision/)
40. Weiyun Wang, Zhe Chen, Wenhai Wang, Yue Cao, Yangzhou Liu, Zhangwei Gao, Jinguo Zhu, Xizhou Zhu, Lewei Lu, Yu Qiao, and Jifeng Dai. 2024b. [Enhancing the reasoning ability of multimodal large language models via mixed preference optimization](https://md.research.elamur.ai/free/en/papers/wang-2024-enhancing-reasoning-ability-multimodal-large/). arXiv preprint arXiv:2411.10442.
41. Gabriela Alves Werb, Patrick Felka, Lisa Reichenbach, Susanne Walter, and Ece Yalcin-Roder. 2024. Geospatial Data and Multimodal Fact-Checking for Validating Company Data. In 2024 IEEE International Conference on Big Data (BigData), pages 3329–3332. ISSN: 2573-2978. [find](https://scholar.google.com/scholar?q=Gabriela+Alves+Werb%2C+Patrick+Felka%2C+Lisa+Reichenbach%2C+Susanne+Walter%2C+and+Ece+Yalcin%2DRoder%2E+2024%2E+Geospatial+Data+and+Multimodal+Fact%2DChecking+for+Validating+Company+Data%2E+In+2024+IEEE+International+C)
42. Thomas Wolf, Lysandre Debut, Victor Sanh, Julien Chaumond, Clement Delangue, Anthony Moi, Pier-ric Cistac, Tim Rault, Rémi Louf, Morgan Funtowicz, Joe Davison, Sam Shleifer, Patrick von Platen, Clara Ma, Yacine Jernite, Julien Plu, Canwen Xu, Teven Le Scao, Sylvain Gugger, and 3 others. 2020. [Transf…](https://md.research.elamur.ai/free/en/papers/wolf-2020-transformers-state-art-natural-language/)
43. Shuai Yuan, Guancong Lin, Lixian Zhang, Runmin Dong, Jinxiao Zhang, Shuang Chen, Juepeng Zheng, Jie Wang, and Haohuan Fu. 2024. Fusu: a multi-temporal-source land use change segmentation dataset for fine-grained urban semantic understanding. In Proceedings of the 38th International Conference on Neu… [find](https://scholar.google.com/scholar?q=Shuai+Yuan%2C+Guancong+Lin%2C+Lixian+Zhang%2C+Runmin+Dong%2C+Jinxiao+Zhang%2C+Shuang+Chen%2C+Juepeng+Zheng%2C+Jie+Wang%2C+and+Haohuan+Fu%2E+2024%2E+Fusu%3A+a+multi%2Dtemporal%2Dsource+land+use+change+segmentation+dataset+for+f)

*Updated 2 November 2026*