{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T18:57:43Z","timestamp":1772823463666,"version":"3.50.1"},"reference-count":30,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,12,4]],"date-time":"2025-12-04T00:00:00Z","timestamp":1764806400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Artif. Intell."],"abstract":"<jats:sec>\n                    <jats:title>Introduction<\/jats:title>\n                    <jats:p>Nature finance involves complex, multi-dimensional challenges that require analytical frameworks to assess risks, impacts, dependencies, and systemic resilience. Existing financial systems lack structured tools to map dependencies between natural capital and financial assets. To address this, we introduce NatureKG, the first ontology and instantiated knowledge graph (KG) specifically tailored to nature finance, aiming to support financial institutions in assessing environmental risks, impacts, and dependencies systematically.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>We designed a domain ontology grounded in ENCORE, the Science-Based Targets Network (SBTN), and peer-reviewed literature. This ontology defines entities such as Actions, Drivers of Nature Loss, Value Chains, Evidence, and Sources. The ontology was instantiated into NatureKG within Neo4j, consisting of 320 nodes and 540 relationships curated by domain experts. As a proof of concept, we constructed a Text2Cypher dataset and fine-tuned three open-source large language models (Phi-3, LLaMA-3.1-8B, and Mistral-7B) to translate natural language queries into Cypher graph queries. The models were trained and evaluated under different dataset split strategies (paraphrase, cypher-level, and generalization) using metrics such as BLEU, exact match, execution accuracy, and Macro F1 scores.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Phi-3 achieved the highest execution accuracy (0.21) and Macro F1 score (0.56), demonstrating better structural and reasoning capability under paraphrase and schema generalization splits. LLaMA-3.1-8B exhibited balanced performance, while Mistral-7B lagged across most metrics. The results indicate that smaller, fine-tuned models can generalize effectively in low-resource, domain-specific settings, validating the feasibility of LLM-assisted querying for nature finance.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Discussion<\/jats:title>\n                    <jats:p>Despite modest initial accuracy, this feasibility study establishes a baseline for integrating domain-specific ontologies with AI systems. NatureKG offers a reusable foundation for representing environmental risks, dependencies, and interventions, with potential to enhance transparency and scalability in sustainable finance decision support. Future work should expand dataset diversity, sectoral coverage beyond the built environment, and refine model reasoning through larger, domain-aligned data catalogues.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/frai.2025.1693843","type":"journal-article","created":{"date-parts":[[2025,12,4]],"date-time":"2025-12-04T14:16:33Z","timestamp":1764857793000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["NatureKG: an ontology and knowledge graph for nature finance with a Text2Cypher application"],"prefix":"10.3389","volume":"8","author":[{"given":"Neetu","family":"Kushwaha","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alok","family":"Singh","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hassan Aftab","family":"Sheikh","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1965","published-online":{"date-parts":[[2025,12,4]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2404.14219","article-title":"Phi-3 technical report: a highly capable language model locally on your phone","author":"Abdin","year":"2024","journal-title":"arXiv preprint arXiv:2404.14219"},{"key":"B2","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3641289","article-title":"A survey on evaluation of large language models","volume":"15","author":"Chang","year":"2024","journal-title":"ACM Trans. Intell. Syst. Technol"},{"key":"B3","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2107.03374","article-title":"Evaluating large language models trained on code","author":"Chen","year":"2021","journal-title":"arXiv preprint arXiv:2107"},{"key":"B4","unstructured":"Kunming-Montreal Global Biodiversity Framework\n          \n          2022"},{"key":"B5","volume-title":"The Economics of Biodiversity: The Dasgupta Review (Full Report)","author":"Dasgupta","year":"2021"},{"key":"B6","volume-title":"Financing Nature: Closing the Global Biodiversity Financing Gap","author":"Deutz","year":"2020"},{"key":"B7","volume-title":"Finance and Biodiversity: Overview of Initiatives for Financial Institutions","year":"2021"},{"key":"B8","doi-asserted-by":"crossref","first-page":"351","DOI":"10.18653\/v1\/P18-1033","article-title":"\u201cImproving text-to-sql evaluation methodology,\u201d","volume-title":"Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","author":"Finegan-Dollak","year":"2018"},{"key":"B9","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2407.21783","article-title":"The Llama 3 herd of models","author":"Grattafiori","year":"2024","journal-title":"arXiv preprint"},{"key":"B10","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2305.15066","article-title":"Gpt4graph: can large language models understand graph structured data? An empirical evaluation and benchmarking","author":"Guo","year":"2023","journal-title":"arXiv preprint arXiv:2308.06661"},{"key":"B11","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2403.14280","article-title":"Large language models for blockchain security: a systematic literature review","author":"He","year":"2024","journal-title":"arXiv preprint arXiv:2403.14280"},{"key":"B12","first-page":"5187","article-title":"\u201cLora: low-rank adaptation of large language models,\u201d","volume-title":"Proceedings of the 40th International Conference on Machine Learning (ICML)","author":"Hu","year":"2022"},{"key":"B13","doi-asserted-by":"publisher","first-page":"494","DOI":"10.1109\/TNNLS.2021.3070843","article-title":"A survey on knowledge graphs: Representation, acquisition, and applications","volume":"33","author":"Ji","year":"2021","journal-title":"IEEE Trans. Neural Netw. Learn. Syst"},{"key":"B14","first-page":"22199","article-title":"\u201cLarge language models are zero-shot reasoners,\u201d","volume-title":"Proceedings of the 36th International Conference on Neural Information Processing Systems (NeurIPS'22)","author":"Kojima","year":"2022"},{"key":"B15","unstructured":"Mistral 7b\n          \n          2023"},{"key":"B16","year":"2023","journal-title":"Encore: Exploring Natural Capital Opportunities, Risks and Exposure. Sector Dependency Tool on Nature and Ecosystem Services"},{"key":"B17","unstructured":"Neo4j Graph Database\n          \n          2024"},{"key":"B18","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2412.10064","article-title":"Text2Cypher: bridging natural language and graph databases","author":"Ozsoy","year":"2024","journal-title":"arXiv preprint"},{"key":"B19","first-page":"311","article-title":"\u201cBleu: a method for automatic evaluation of machine translation,\u201d","volume-title":"Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics","author":"Papineni","year":"2002"},{"key":"B20","volume-title":"Science-Based Targets for Nature: Initial Guidance for Business","year":"2020"},{"key":"B21","doi-asserted-by":"publisher","first-page":"1","DOI":"10.4018\/JGIM.335125","article-title":"Exploring the potential of large language models in supply chain management: a study using big data","volume":"32","author":"Srivastava","year":"2024","journal-title":"J. Glob. Inform. Manag"},{"key":"B22","volume-title":"Recommendations v1.0: Final Framework for Assessing and Disclosing Nature-Related Financial Risks","year":"2023"},{"key":"B23","unstructured":"Hf Models\n          \n          2024"},{"key":"B24","unstructured":"Unsloth ai - Open Source Fine-Tuning for Llms\n          \n          2024"},{"key":"B25","doi-asserted-by":"crossref","first-page":"168","DOI":"10.18653\/v1\/2024.climatenlp-1.13","article-title":"\u201cStructuring sustainability reports for environmental standards with llms guided by ontology,\u201d","volume-title":"Proceedings of the 1st Workshop on Natural Language Processing Meets Climate Change (ClimateNLP 2024)","author":"Usmanova","year":"2024"},{"key":"B26","volume-title":"SDG Sector Roadmaps: Guidelines to Accelerate Sector Transformation","year":"2021"},{"key":"B27","article-title":"Bloomberggpt: a large language model for finance","author":"Wu","year":"2023","journal-title":"arXiv preprint"},{"key":"B28","doi-asserted-by":"publisher","first-page":"2397630","DOI":"10.1080\/17517575.2024.2397630","article-title":"Decentralized finance (DeFi): a paradigm shift in the Fintech","volume":"18","author":"Xu","year":"2024","journal-title":"Inform. Syst"},{"key":"B29","doi-asserted-by":"crossref","first-page":"3911","DOI":"10.18653\/v1\/D18-1425","article-title":"\u201cSpider: a large-scale human-labeled dataset for complex and cross-domain semantic parsing and text-to-sql task,\u201d","volume-title":"Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing (EMNLP)","author":"Yu","year":"2018"},{"key":"B30","unstructured":"\u201cOntosustain: towards an ontology for corporate sustainability reporting,\u201d\n          \n          168\n          177\n          \n            \n              Zhou\n              Y.\n            \n            \n              Perzylo\n              A.\n            \n          \n          Proceedings of the ISWC 2023 Posters, Demos and Industry Tracks: From Novel Ideas to Industrial Practice co-located with 22nd International Semantic Web Conference (ISWC 2023), volume 3632 of CEUR Workshop Proceedings\n          \n          2023"}],"container-title":["Frontiers in Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2025.1693843\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,4]],"date-time":"2025-12-04T14:16:38Z","timestamp":1764857798000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2025.1693843\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,4]]},"references-count":30,"alternative-id":["10.3389\/frai.2025.1693843"],"URL":"https:\/\/doi.org\/10.3389\/frai.2025.1693843","relation":{},"ISSN":["2624-8212"],"issn-type":[{"value":"2624-8212","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12,4]]},"article-number":"1693843"}}