EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

BioChat: A Domain-Specific Biodiversity Question-Answering System to Support Sustainable Conservation Decision-Making

Dong-Seok Jang, Jae-Sik Yi, Hyung-Bae Jeon, Youn-Sik Hong

Sustainability · 31.12.2025 · 18 (1) · 396

DOI: 10.3390/su18010396 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sustainability, online erschienen am 31.12.2025. Verfasst von Dong-Seok Jang und 3 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 42 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Institute of Biological Resources (NIBR), Ministry of Climate, Energy and Environment.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Biodiversity knowledge is fundamental to conservation planning and sustainable environmental decision-making; however, general-purpose Large Language Models (LLMs) frequently produce hallucinations when responding to biodiversity-related queries. To address this challenge, we propose BioChat, a domain-specific question-answering system that integrates a Retrieval-Augmented Generation (RAG) framework with a Re-Ranker–based retrieval and routing mechanism. The system is built upon a verified biodiversity dataset curated by the National Institute of Biological Resources (NIBR), comprising 25,593 species and approximately 970,000 structured data points. We systematically evaluate the effects of embedding selection, routing strategy, and generative model choice on factual accuracy and hallucination mitigation. Experimental results show that the proposed Re-Ranker-based routing strategy significantly improves system reliability, increasing factual accuracy from 47.9% to 71.3% and reducing hallucination rate from 34.0% to 24.4% compared with Naive RAG baseline. Among the evaluated LLMs, Qwen2-7B-Instruct achieves the highest factual accuracy, while Gemma-2-9B-Instruct demonstrates superior hallucination control. By delivering transparent, verifiable, and context-grounded biodiversity information, BioChat supports environmental education, citizen science, and evidence-based conservation policy development. This work demonstrates how trustworthy AI systems can serve as sustainability-enabling infrastructure, facilitating reliable access to biodiversity knowledge for long-term ecological conservation and informed public decision-making.

Förderung

  • National Institute of Biological Resources (NIBR), Ministry of Climate, Energy and Environment

Zitieren

APA

Jang, D., Yi, J., Jeon, H., & Hong, Y. (2025). BioChat: A Domain-Specific Biodiversity Question-Answering System to Support Sustainable Conservation Decision-Making. Sustainability, 18(1), 396. https://doi.org/10.3390/su18010396

Vancouver

Jang D, Yi J, Jeon H, Hong Y. BioChat: A Domain-Specific Biodiversity Question-Answering System to Support Sustainable Conservation Decision-Making. Sustainability. 2025;18(1):396. doi:10.3390/su18010396

BibTeX
@article{Jang2025,
  author = {Jang, Dong-Seok and Yi, Jae-Sik and Jeon, Hyung-Bae and Hong, Youn-Sik},
  title = {BioChat: A Domain-Specific Biodiversity Question-Answering System to Support Sustainable Conservation Decision-Making},
  journal = {Sustainability},
  year = {2025},
  volume = {18},
  number = {1},
  pages = {396},
  doi = {10.3390/su18010396}
}
Kostenlos starten →