---
title: "Coordinates from Context — paper by Masis and O'Connor (2026)"
description: "Building on this, they propose an end-to-end approach in two variants: Direct: the LLM predicts the area on its own. 44 references."
authors: ["Tessa Masis", "Brendan O'Connor"]
year: 2026
venue: "Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)"
source: "https://aclanthology.org/2026.eacl-long.74/"
doi: "10.18653/v1/2026.eacl-long.74"
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/masis-2026-coordinates-context-llms-ground-complex/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/masis-2026-coordinates-context-llms-ground-complex/)

[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/11/) / Coordinates from Context: Using LLMs to Ground Complex Location References

# Coordinates from Context: Using LLMs to Ground Complex Location References

**Authors:** [Tessa Masis](https://md.research.elamur.ai/free/en/authors/tessa-masis/) and [Brendan O'Connor](https://md.research.elamur.ai/free/en/authors/brendan-o-connor/) · **Year:** 2026 · **Venue:** [Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)](https://md.research.elamur.ai/free/en/venues/eacl/) ([EACL 2026](https://md.research.elamur.ai/free/en/venues/eacl/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.eacl-long.74/) · [PDF](https://aclanthology.org/2026.eacl-long.74.pdf) · [DOI 10.18653/v1/2026.eacl-long.74](https://doi.org/10.18653/v1/2026.eacl-long.74) · [OpenAlex](https://openalex.org/W7140081407)

**Citations:** 1 citations (OpenAlex, 2026-10-14)

## Summary

The paper addresses geocoding of compositional location references. These are places described relative to other toponyms rather than by name, such as a spot lying between two towns. Standard geocoders cannot ground such descriptions because they only resolve the named places inside the phrase, and the target area usually has no entry in a geographic database.

The authors first test LLMs on the GeoCode test set, which contains English Wikipedia descriptions linked to OpenStreetMap. One test measures recalling geospatial facts (coordinates of a named place). The other measures reasoning over supplied coordinates to locate an unnamed area. The models handled reasoning better than knowledge recall.

Building on this, they propose an end-to-end approach in two variants:
- **Direct:** the LLM predicts the area on its own.
- **Geoparser-augmented:** a traditional geoparser supplies coordinates of the mentioned places, and the LLM reasons over them.

Locations are represented as bounding boxes, which capture an area's extent while staying simple enough for an LLM to work with. The methods outperform prior work, and a relatively small fine-tuned model performs comparably to much larger off-the-shelf LLMs. The work suggests a practical route to grounding vague or unnamed regions in text.

## Key points

- **Data and models:** The evaluation uses the 1,000 manually curated test descriptions from GeoCode (Laparra and Bethard, 2020), the only existing dataset for this task. The off-the-shelf models are Qwen2.5-72B-Instruct, Llama3.3-70B-Instruct and Llama3.1-405B-Instruct, each prompted with two examples (few-shot).
- **Metrics:** There are five in total: coverage, distance error, and area precision, recall and F1. The area metrics measure how much the predicted bounding box overlaps the gold one.
- **Choosing a variant:** The Geoparser-augmented variant tends to produce larger, less precise boxes. The LLM often simply takes the extreme coordinates of the mentioned places. When area precision matters, or no geoparser is available, the authors recommend Direct prompting with a large model such as Llama 405B.
- **Common error:** Models frequently flip the sign of latitude or longitude. This happens more with Qwen and with smaller models, and less in the Geoparser-augmented setting.
- **Release and limitations:** The best fine-tuned model is published on Hugging Face (tmasis/geocoding-complex-location-references). The study is limited to English Wikipedia data and uses only open-weight models, chosen for privacy reasons.

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

📚 Shelves (6): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 16,667 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 16,194 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 16,039 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 15,891 works · [🤝 Social Sciences](https://md.research.elamur.ai/free/en/shelves/social-sciences/) · 1,772 works · [🗺️ Geography, Planning and Development](https://md.research.elamur.ai/free/en/shelves/social-sciences/geography-planning-and-development/) · 6 works

## Cite

Cite as: Tessa Masis and Brendan O'Connor. 2026. Coordinates from Context: Using LLMs to Ground Complex Location References. Proceedings of the 19th Conference of the European Chapter 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{masis2026coordinates,
  title = {{Coordinates from Context: Using LLMs to Ground Complex Location References}},
  author = {Tessa Masis and Brendan O'Connor},
  booktitle = {Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)},
  year = {2026},
  doi = {10.18653/v1/2026.eacl-long.74},
  url = {https://doi.org/10.18653/v1/2026.eacl-long.74}
}
```

- [← previous Conversational Assistants to Support Patients with Heart Failure: Comparing a Neurosymbolic Architecture with GPT](https://md.research.elamur.ai/free/en/papers/tayal-2026-conversational-assistants-support-patients-heart/)
- [next → Coreference annotation for characterising characters in literary works in Portuguese](https://md.research.elamur.ai/free/en/papers/santos-2026-marcacao-de-correferencia-para-caracterizacao/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/11/)

## References

44 references, 6 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Unsloth AI, Daniel Han-Chen, and Michael Han-Chen. 2025. Unsloth. [https://github.com/unslothai/](https://github.com/unslothai/) unsloth. [↗](https://github.com/unslothai/)
2. Hussein S Al-Olimat, Valerie L Shalin, Krishnaprasad Thirunarayan, and Joy Prakash Sain. 2019. Towards geocoding spatial expressions (vision paper). In Proceedings of the 27th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems, pages 75–78. [find](https://scholar.google.com/scholar?q=Hussein+S+Al%2DOlimat%2C+Valerie+L+Shalin%2C+Krishnaprasad+Thirunarayan%2C+and+Joy+Prakash+Sain%2E+2019%2E+Towards+geocoding+spatial+expressions+%28vision+paper%29%2E+In+Proceedings+of+the+27th+ACM+SIGSPATIAL+Internati)
3. Prabin Bhandari, Antonios Anastasopoulos, and Dieter Pfoser. 2023. Are large language models geospatially knowledgeable? In Proceedings of the 31st ACM International Conference on Advances in Geographic Information Systems, pages 1–4. [find](https://scholar.google.com/scholar?q=Prabin+Bhandari%2C+Antonios+Anastasopoulos%2C+and+Dieter+Pfoser%2E+2023%2E+Are+large+language+models+geospatially+knowledgeable%3F+In+Proceedings+of+the+31st+ACM+International+Conference+on+Advances+in+Geograph)
4. Geoff Boeing. 2025. Modeling and analyzing urban networks and amenities with OSMnx. Geographical Analysis. [find](https://scholar.google.com/scholar?q=Geoff+Boeing%2E+2025%2E+Modeling+and+analyzing+urban+networks+and+amenities+with+OSMnx%2E+Geographical+Analysis%2E)
5. Yida Chen, Yixian Gan, Sijia Li, Li Yao, and Xiaohan Zhao. 2023. More than correlation: Do large language models learn causal representations of space? arXiv preprint arXiv:2312.16257. — [arXiv:2312.16257](https://arxiv.org/abs/2312.16257) [find](https://scholar.google.com/scholar?q=Yida+Chen%2C+Yixian+Gan%2C+Sijia+Li%2C+Li+Yao%2C+and+Xiaohan+Zhao%2E+2023%2E+More+than+correlation%3A+Do+large+language+models+learn+causal+representations+of+space%3F+arXiv+preprint+arXiv%3A2312%2E16257%2E+%E2%80%94+%5BarXiv%3A2312%2E1)
6. Grant DeLozier, Jason Baldridge, and Loretta London. 2015. Gazetteer-independent toponym resolution using geographic word profiles. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 29. [find](https://scholar.google.com/scholar?q=Grant+DeLozier%2C+Jason+Baldridge%2C+and+Loretta+London%2E+2015%2E+Gazetteer%2Dindependent+toponym+resolution+using+geographic+word+profiles%2E+In+Proceedings+of+the+AAAI+Conference+on+Artificial+Intelligence%2C+vo)
7. Mark Dredze, Michael J Paul, Shane Bergsma, and Hieu Tran. 2013. Carmen: A Twitter Geolocation System with Applications to Public Health. In AAAI Workshop on Expanding the Boundaries of Health Informatics Using AI (HIAI), volume 23, page 45. Citeseer. [find](https://scholar.google.com/scholar?q=Mark+Dredze%2C+Michael+J+Paul%2C+Shane+Bergsma%2C+and+Hieu+Tran%2E+2013%2E+Carmen%3A+A+Twitter+Geolocation+System+with+Applications+to+Public+Health%2E+In+AAAI+Workshop+on+Expanding+the+Boundaries+of+Health+Informa)
8. Abhimanyu Dubey, Abhinav Jauhri, Abhinav Pandey, Abhishek Kadian, Ahmad Al-Dahle, Aiesha Letman, Akhil Mathur, Alan Schelten, Amy Yang, Angela Fan, et al. 2024. [The Llama 3 Herd of Models](https://md.research.elamur.ai/free/en/papers/grattafiori-2024-llama-3-herd-models/). arXiv preprint arXiv:2407.21783.
9. Sam Dupre, Lindsay Spell, and Paul Jung. 2022. Geospatial Data Disclosure Avoidance and the Census. Select Topics in International Censuses (STIC 1, 1 (2022), 1–9. [find](https://scholar.google.com/scholar?q=Sam+Dupre%2C+Lindsay+Spell%2C+and+Paul+Jung%2E+2022%2E+Geospatial+Data+Disclosure+Avoidance+and+the+Census%2E+Select+Topics+in+International+Censuses+%28STIC+1%2C+1+%282022%29%2C+1%E2%80%939%2E)
10. Fahim Faisal and Antonios Anastasopoulos. 2023. Geographic and geopolitical biases of language models. In Proceedings of the 3rd Workshop on Multi-lingual Representation Learning (MRL), pages 139–163. [find](https://scholar.google.com/scholar?q=Fahim+Faisal+and+Antonios+Anastasopoulos%2E+2023%2E+Geographic+and+geopolitical+biases+of+language+models%2E+In+Proceedings+of+the+3rd+Workshop+on+Multi%2Dlingual+Representation+Learning+%28MRL%29%2C+pages+139%E2%80%93163%2E)
11. Nathan Godey, Éric Villemonte De La Clergerie, and Benoît Sagot. 2024. On the scaling laws of geographical representation in language models. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 12416– 124… [find](https://scholar.google.com/scholar?q=Nathan+Godey%2C+%C3%89ric+Villemonte+De+La+Clergerie%2C+and+Beno%C3%AEt+Sagot%2E+2024%2E+On+the+scaling+laws+of+geographical+representation+in+language+models%2E+In+Proceedings+of+the+2024+Joint+International+Conference+)
12. Wes Gurnee and Max Tegmark. 2024. Language models represent space and time. In The Twelfth International Conference on Learning Representations. [find](https://scholar.google.com/scholar?q=Wes+Gurnee+and+Max+Tegmark%2E+2024%2E+Language+models+represent+space+and+time%2E+In+The+Twelfth+International+Conference+on+Learning+Representations%2E)
13. Karlyn Harrod, Prabin Bhandari, and Antonios Anastasopoulos. 2024. From Text to Maps: LLM-Driven Extraction and Geotagging of Epidemiological Data. In Proceedings of the Third Workshop on NLP for Positive Impact, pages 258–270. [find](https://scholar.google.com/scholar?q=Karlyn+Harrod%2C+Prabin+Bhandari%2C+and+Antonios+Anastasopoulos%2E+2024%2E+From+Text+to+Maps%3A+LLM%2DDriven+Extraction+and+Geotagging+of+Epidemiological+Data%2E+In+Proceedings+of+the+Third+Workshop+on+NLP+for+Posi)
14. Junlin He, Tong Nie, and Wei Ma. 2025. Geolocation representation from large language models are generic enhancers for spatio-temporal learning. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 39, pages 17094–17104. [find](https://scholar.google.com/scholar?q=Junlin+He%2C+Tong+Nie%2C+and+Wei+Ma%2E+2025%2E+Geolocation+representation+from+large+language+models+are+generic+enhancers+for+spatio%2Dtemporal+learning%2E+In+Proceedings+of+the+AAAI+Conference+on+Artificial+Int)
15. Xuke Hu, Zhiyong Zhou, Hao Li, Yingjie Hu, Fuqiang Gu, Jens Kersten, Hongchao Fan, and Friederike Klan. 2023a. Location reference recognition from texts: A survey and comparison. ACM Computing Surveys, 56(5):1–37. [find](https://scholar.google.com/scholar?q=Xuke+Hu%2C+Zhiyong+Zhou%2C+Hao+Li%2C+Yingjie+Hu%2C+Fuqiang+Gu%2C+Jens+Kersten%2C+Hongchao+Fan%2C+and+Friederike+Klan%2E+2023a%2E+Location+reference+recognition+from+texts%3A+A+survey+and+comparison%2E+ACM+Computing+Surveys)
16. Yingjie Hu, Gengchen Mai, Chris Cundy, Kristy Choi, Ni Lao, Wei Liu, Gaurish Lakhanpal, Ryan Zhenqi Zhou, and Kenneth Joseph. 2023b. Geo-knowledge-guided GPT models improve the extraction of location descriptions from disaster-related social media messages. International Journal of Geographical Info… [find](https://scholar.google.com/scholar?q=Yingjie+Hu%2C+Gengchen+Mai%2C+Chris+Cundy%2C+Kristy+Choi%2C+Ni+Lao%2C+Wei+Liu%2C+Gaurish+Lakhanpal%2C+Ryan+Zhenqi+Zhou%2C+and+Kenneth+Joseph%2E+2023b%2E+Geo%2Dknowledge%2Dguided+GPT+models+improve+the+extraction+of+location+)
17. Ilya Ilyankou, Meihui Wang, Stefano Cavazzi, and James Haworth. 2024. Quantifying Geospatial in the Common Crawl Corpus. In Proceedings of the 32nd ACM International Conference on Advances in Geographic Information Systems, pages 585–588. [find](https://scholar.google.com/scholar?q=Ilya+Ilyankou%2C+Meihui+Wang%2C+Stefano+Cavazzi%2C+and+James+Haworth%2E+2024%2E+Quantifying+Geospatial+in+the+Common+Crawl+Corpus%2E+In+Proceedings+of+the+32nd+ACM+International+Conference+on+Advances+in+Geograph)
18. Yuhan Ji, Song Gao, Ying Nie, Ivan Majić, and Krzysztof Janowicz. 2025. Foundation models for geospatial reasoning: assessing the capabilities of large language models in understanding geometries and topological spatial relations. International Journal of Geographical Information Science, pages 1–… [find](https://scholar.google.com/scholar?q=Yuhan+Ji%2C+Song+Gao%2C+Ying+Nie%2C+Ivan+Majic%CC%81%2C+and+Krzysztof+Janowicz%2E+2025%2E+Foundation+models+for+geospatial+reasoning%3A+assessing+the+capabilities+of+large+language+models+in+understanding+geometries+and)
19. Christopher B Jones, Ross S Purves, Paul D Clough, and Hideo Joho. 2008. Modelling vague places with knowledge from the web. International Journal of Geographical Information Science, 22(10):1045– 1065. [find](https://scholar.google.com/scholar?q=Christopher+B+Jones%2C+Ross+S+Purves%2C+Paul+D+Clough%2C+and+Hideo+Joho%2E+2008%2E+Modelling+vague+places+with+knowledge+from+the+web%2E+International+Journal+of+Geographical+Information+Science%2C+22%2810%29%3A1045%E2%80%93+106)
20. Anna Kruspe, Matthias Häberle, Eike J Hoffmann, Samyo Rode-Hasinger, Karam Abdulahhad, and Xiao Xiang Zhu. 2021. Changes in Twitter geolocations: Insights and suggestions for future usage. In Proceedings of the Seventh Workshop on Noisy User-generated Text (W-NUT 2021), pages 212–221. [find](https://scholar.google.com/scholar?q=Anna+Kruspe%2C+Matthias+H%C3%A4berle%2C+Eike+J+Hoffmann%2C+Samyo+Rode%2DHasinger%2C+Karam+Abdulahhad%2C+and+Xiao+Xiang+Zhu%2E+2021%2E+Changes+in+Twitter+geolocations%3A+Insights+and+suggestions+for+future+usage%2E+In+Proceedi)
21. Sayali Kulkarni, Shailee Jain, Mohammad Javad Hosseini, Jason Baldridge, Eugene Ie, and Li Zhang. 2021. Multi-Level Gazetteer-Free Geocoding. In Proceedings of Second International Combined Workshop on Spatial Language Understanding and Grounded Communication for Robotics, pages 79– 88. [find](https://scholar.google.com/scholar?q=Sayali+Kulkarni%2C+Shailee+Jain%2C+Mohammad+Javad+Hosseini%2C+Jason+Baldridge%2C+Eugene+Ie%2C+and+Li+Zhang%2E+2021%2E+Multi%2DLevel+Gazetteer%2DFree+Geocoding%2E+In+Proceedings+of+Second+International+Combined+Workshop+o)
22. Abhinav Kumar and Jyoti Prakash Singh. 2019. Location reference identification from tweets during emergencies: A deep learning approach. International Journal of Disaster Risk Reduction, 33:365–375. [find](https://scholar.google.com/scholar?q=Abhinav+Kumar+and+Jyoti+Prakash+Singh%2E+2019%2E+Location+reference+identification+from+tweets+during+emergencies%3A+A+deep+learning+approach%2E+International+Journal+of+Disaster+Risk+Reduction%2C+33%3A365%E2%80%93375%2E)
23. Edward J Hu, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, Weizhu Chen, et al. 2021. [LoRA: Low-Rank Adaptation of Large Language Models](https://md.research.elamur.ai/free/en/papers/hu-2021-lora-low-rank-adaptation-large/). In International Conference on Learning Representations.
24. Egoitz Laparra and Steven Bethard. 2020. A dataset and evaluation framework for complex geographical description parsing. In Proceedings of the 28th International Conference on Computational Linguistics, pages 936–948. [find](https://scholar.google.com/scholar?q=Egoitz+Laparra+and+Steven+Bethard%2E+2020%2E+A+dataset+and+evaluation+framework+for+complex+geographical+description+parsing%2E+In+Proceedings+of+the+28th+International+Conference+on+Computational+Linguisti)
25. Xuke Hu, Jens Kersten, Friederike Klan, and Sheikh Mastura Farzana. 2024. Toponym resolution leveraging lightweight and open-source large language models and geo-knowledge. International Journal of Geographical Information Science, pages 1–28. [find](https://scholar.google.com/scholar?q=Xuke+Hu%2C+Jens+Kersten%2C+Friederike+Klan%2C+and+Sheikh+Mastura+Farzana%2E+2024%2E+Toponym+resolution+leveraging+lightweight+and+open%2Dsource+large+language+models+and+geo%2Dknowledge%2E+International+Journal+of+Ge)
26. Kathy Lee, Ankit Agrawal, and Alok Choudhary. 2013. Real-time disease surveillance using Twitter data: Demonstration on flu and cancer. In Proceedings of the 19th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pages 1474–1477. [find](https://scholar.google.com/scholar?q=Kathy+Lee%2C+Ankit+Agrawal%2C+and+Alok+Choudhary%2E+2013%2E+Real%2Dtime+disease+surveillance+using+Twitter+data%3A+Demonstration+on+flu+and+cancer%2E+In+Proceedings+of+the+19th+ACM+SIGKDD+International+Conference+o)
27. Bryan Li, Samar Haider, and Chris Callison-Burch. 2024. This land is your, my land: Evaluating geopolitical bias in language models through territorial disputes. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Techn… [find](https://scholar.google.com/scholar?q=Bryan+Li%2C+Samar+Haider%2C+and+Chris+Callison%2DBurch%2E+2024%2E+This+land+is+your%2C+my+land%3A+Evaluating+geopolitical+bias+in+language+models+through+territorial+disputes%2E+In+Proceedings+of+the+2024+Conference+)
28. Jimin Wang and Yingjie Hu. 2019. Enhancing spatial and textual analysis with EUPEG: An extensible and unified platform for evaluating geoparsers. Transactions in GIS, 23(6):1393–1419. [find](https://scholar.google.com/scholar?q=Jimin+Wang+and+Yingjie+Hu%2E+2019%2E+Enhancing+spatial+and+textual+analysis+with+EUPEG%3A+An+extensible+and+unified+platform+for+evaluating+geoparsers%2E+Transactions+in+GIS%2C+23%286%29%3A1393%E2%80%931419%2E)
29. Mahrokh Abdollahi Lorestani, Thilina Ranbaduge, and Thierry Rakotoarivelo. 2024. Privacy risk in geodata: A survey. arXiv preprint arXiv:2402.03612. — [arXiv:2402.03612](https://arxiv.org/abs/2402.03612) [find](https://scholar.google.com/scholar?q=Mahrokh+Abdollahi+Lorestani%2C+Thilina+Ranbaduge%2C+and+Thierry+Rakotoarivelo%2E+2024%2E+Privacy+risk+in+geodata%3A+A+survey%2E+arXiv+preprint+arXiv%3A2402%2E03612%2E+%E2%80%94+%5BarXiv%3A2402%2E03612%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F2402%2E036)
30. Zengzhi Wang, Fan Zhou, Xuefeng Li, and Pengfei Liu. 2025. Octothinker: Mid-training incentivizes reinforcement learning scaling. arXiv preprint arXiv:2506.20512. — [arXiv:2506.20512](https://arxiv.org/abs/2506.20512) [find](https://scholar.google.com/scholar?q=Zengzhi+Wang%2C+Fan+Zhou%2C+Xuefeng+Li%2C+and+Pengfei+Liu%2E+2025%2E+Octothinker%3A+Mid%2Dtraining+incentivizes+reinforcement+learning+scaling%2E+arXiv+preprint+arXiv%3A2506%2E20512%2E+%E2%80%94+%5BarXiv%3A2506%2E20512%5D%28https%3A%2F%2Farxiv%2Eor)
31. Sara Vera Marjanović, Arkil Patel, Vaibhav Adlakha, Milad Aghajohari, Parishad BehnamGhader, Mehar Bhatia, Aditi Khandelwal, Austin Kraft, Benno Krojer, Xing Han Lù, et al. 2025. DeepSeek-R1 Thoughtology: Let’s think about LLM Reasoning. arXiv preprint arXiv:2504.07128. [find](https://scholar.google.com/scholar?q=Sara+Vera+Marjanovic%CC%81%2C+Arkil+Patel%2C+Vaibhav+Adlakha%2C+Milad+Aghajohari%2C+Parishad+BehnamGhader%2C+Mehar+Bhatia%2C+Aditi+Khandelwal%2C+Austin+Kraft%2C+Benno+Krojer%2C+Xing+Han+L%C3%B9%2C+et+al%2E+2025%2E+DeepSeek%2DR1+Thoughto)
32. Liuchang Xu, Shuo Zhao, Qingming Lin, Luyao Chen, Qianqian Luo, Sensen Wu, Xinyue Ye, Hailin Feng, and Zhenhong Du. 2024. Evaluating large language models on spatial tasks: A multi-task benchmarking study. arXiv preprint arXiv:2408.14438. — [arXiv:2408.14438](https://arxiv.org/abs/2408.14438) [find](https://scholar.google.com/scholar?q=Liuchang+Xu%2C+Shuo+Zhao%2C+Qingming+Lin%2C+Luyao+Chen%2C+Qianqian+Luo%2C+Sensen+Wu%2C+Xinyue+Ye%2C+Hailin+Feng%2C+and+Zhenhong+Du%2E+2024%2E+Evaluating+large+language+models+on+spatial+tasks%3A+A+multi%2Dtask+benchmarking+s)
33. Tessa Masis and Brendan O’Connor. 2024. Where on earth do users say they are?: Geo-entity linking for noisy multilingual user input. In Proceedings of the Sixth Workshop on Natural Language Processing and Computational Social Science (NLP+CSS 2024), pages 86–98, Mexico City, Mexico. Association for… [find](https://scholar.google.com/scholar?q=Tessa+Masis+and+Brendan+O%E2%80%99Connor%2E+2024%2E+Where+on+earth+do+users+say+they+are%3F%3A+Geo%2Dentity+linking+for+noisy+multilingual+user+input%2E+In+Proceedings+of+the+Sixth+Workshop+on+Natural+Language+Processing)
34. Grégoire Mialon, Roberto Dessì, Maria Lomeli, Christoforos Nalmpantis, Ram Pasunuru, Roberta Raileanu, Baptiste Rozière, Timo Schick, Jane Dwivedi-Yu, Asli Celikyilmaz, et al. 2023. [Augmented language models: a survey](https://md.research.elamur.ai/free/en/papers/mialon-2023-augmented-language-models-survey/). Transactions on Machine Learning Research, 2023.
35. Kent O’Sullivan, Nicole R Schneider, and Hanan Samet. 2024. Metric reasoning in large language models. In Proceedings of the 32nd ACM International Conference on Advances in Geographic Information Systems, pages 501–504. [find](https://scholar.google.com/scholar?q=Kent+O%E2%80%99Sullivan%2C+Nicole+R+Schneider%2C+and+Hanan+Samet%2E+2024%2E+Metric+reasoning+in+large+language+models%2E+In+Proceedings+of+the+32nd+ACM+International+Conference+on+Advances+in+Geographic+Information+Sys)
36. Murat Ozer, Michael Zidar, Rustu Deryol, Said Varli-oglu, Ibrahim Sevki Eldivan, and Halil Akbas. 2020. Creating a real-time geocoding system: implications of open source for the public safety. In 2020 International Conference on Computational Science and Computational Intelligence (CSCI), pages 118… [find](https://scholar.google.com/scholar?q=Murat+Ozer%2C+Michael+Zidar%2C+Rustu+Deryol%2C+Said+Varli%2Doglu%2C+Ibrahim+Sevki+Eldivan%2C+and+Halil+Akbas%2E+2020%2E+Creating+a+real%2Dtime+geocoding+system%3A+implications+of+open+source+for+the+public+safety%2E+In+202)
37. Yibo Yan and Joey Lee. 2024. Georeasoner: Reasoning on geospatially grounded context for natural language understanding. In Proceedings of the 33rd ACM International Conference on Information and Knowledge Management, pages 4163–4167. [find](https://scholar.google.com/scholar?q=Yibo+Yan+and+Joey+Lee%2E+2024%2E+Georeasoner%3A+Reasoning+on+geospatially+grounded+context+for+natural+language+understanding%2E+In+Proceedings+of+the+33rd+ACM+International+Conference+on+Information+and+Know)
38. An Yang, Anfeng Li, Baosong Yang, Beichen Zhang, Binyuan Hui, Bo Zheng, Bowen Yu, Chang Gao, Chengen Huang, Chenxu Lv, et al. 2025a. [Qwen3 technical report](https://md.research.elamur.ai/free/en/papers/yang-2025-qwen3-technical-report/). arXiv preprint arXiv:2505.09388.
39. An Yang, Baosong Yang, Beichen Zhang, Binyuan Hui, Bo Zheng, Bowen Yu, Chengyuan Li, Dayiheng Liu, Fei Huang, Haoran Wei, et al. 2025b. Qwen2.5 technical report. arXiv preprint arXiv:2412.15115. [find](https://scholar.google.com/scholar?q=An+Yang%2C+Baosong+Yang%2C+Beichen+Zhang%2C+Binyuan+Hui%2C+Bo+Zheng%2C+Bowen+Yu%2C+Chengyuan+Li%2C+Dayiheng+Liu%2C+Fei+Huang%2C+Haoran+Wei%2C+et+al%2E+2025b%2E+Qwen2%2E5+technical+report%2E+arXiv+preprint+arXiv%3A2412%2E15115%2E)
40. Zeyu Zhang and Steven Bethard. 2024. A survey on geocoding: algorithms and datasets for toponym resolution. Language Resources and Evaluation, pages 1–22. [find](https://scholar.google.com/scholar?q=Zeyu+Zhang+and+Steven+Bethard%2E+2024%2E+A+survey+on+geocoding%3A+algorithms+and+datasets+for+toponym+resolution%2E+Language+Resources+and+Evaluation%2C+pages+1%E2%80%9322%2E)
41. Yang Zhou, Hongyi Liu, Zhuoming Chen, Yuandong Tian, and Beidi Chen. 2025. [GSM-Infinite: How Do Your LLMs Behave over Infinitely Increasing Context Length and Reasoning Complexity?](https://md.research.elamur.ai/free/en/papers/zhou-2025-gsm-infinite-llms-behave-over/) arXiv preprint arXiv:2502.05252.
42. Praval Sharma, Ashok Samal, Leen-Kiat Soh, and Deepti Joshi. 2023. A spatially-aware data-driven approach to automatically geocoding non-gazetteer place names. ACM Trans. Spatial Algorithms Syst., 10(1). [find](https://scholar.google.com/scholar?q=Praval+Sharma%2C+Ashok+Samal%2C+Leen%2DKiat+Soh%2C+and+Deepti+Joshi%2E+2023%2E+A+spatially%2Daware+data%2Ddriven+approach+to+automatically+geocoding+non%2Dgazetteer+place+names%2E+ACM+Trans%2E+Spatial+Algorithms+Syst%2E%2C+10%28)
43. Freda Shi, Xinyun Chen, Kanishka Misra, Nathan Scales, David Dohan, Ed H Chi, Nathanael Schärli, and Denny Zhou. 2023. [Large language models can be easily distracted by irrelevant context](https://md.research.elamur.ai/free/en/papers/shi-2023-large-language-models-easily-distracted/). In International Conference on Machine Learning, pages 31210–31227. PMLR.
44. Laura Tateosian, Rachael Guenter, Yi-Peng Yang, and Jean Ristaino. 2017. Tracking 19th century late blight from archival documents using text analytics and geoparsing. In Free and Open Source Software [find](https://scholar.google.com/scholar?q=Laura+Tateosian%2C+Rachael+Guenter%2C+Yi%2DPeng+Yang%2C+and+Jean+Ristaino%2E+2017%2E+Tracking+19th+century+late+blight+from+archival+documents+using+text+analytics+and+geoparsing%2E+In+Free+and+Open+Source+Software)

*Updated 31 October 2026*