20.500.12556/DiRROS-30354 Rapid evidence mapping of soil fauna responses to agricultural management assisted by large language models The exponential growth of scientific literature challenges traditional synthesis methods, limiting our ability to derive broad insights into complex environmental processes. Large language models (LLMs) may help address this challenge by supporting the extraction of structured knowledge from unstructured text. To evaluate and demonstrate this potential in soil science, we developed a multi-module, LLM-assisted knowledge-extraction workflow built on a recently published meta-data-analysis of management–biota interactions as a contextual framework, using an iteratively refined prompt chain to extract directional relationships between agricultural management practices and soil fauna from scientific abstracts. Benchmarking against manually curated datasets showed high precision and recall, while expert-guided iterative development indicated that the information content of abstracts was likely a major practical constraint on extraction performance. To assess interpretative soundness, we applied the workflow in two use cases: an illustrative comparison with the well-established literature on reduced and no-tillage effects on soil fauna, and a knowledge-gap application on biochar and crop-residue retention. The workflow indicated predominantly beneficial reported patterns for crop residue retention, particularly for earthworms and nematodes, whereas biochar showed a more heterogeneous and context-dependent pattern. Overall, results show that LLM-assisted workflows can support rapid, large-scale evidence mapping of soil fauna responses to management practices when formal quantitative syntheses are unavailable. The proposed framework is best understood as a complementary tool for organising and screening dispersed ecological evidence, and not as a substitute for full-text synthesis, effect-size-based meta-analysis, or decision-grade inference. The complete workflow is publicly available and broadly transferable across environmental research domains. text mining knowledge extraction artificial intelligence soil biota biochar crop residues rudarjenje besedil pridobivanje znanja umetna inteligenca talna biota rastlinski ostanki true false true Elsevier Nizozemska Angleški jezik Slovenski jezik © 2026 The Author(s). Neznano 2026-06-23 10:46:19 2026-06-23 10:46:19 2026-06-24 03:46:07 0000-00-00 00:00:00 2026 0 0 Nasl. z nasl. zaslona; Opis vira z dne 19. 6. 2026; Avtorja iz Slovenije: Vid Podpečan, Marko Debeljak; 1-14 str. [article no.] 117890 Vol. 471 2026 0000-00-00 Zaloznikova Objavljeno NiDoloceno 2026-01-13 2026-06-01 2026-06-10 004.8 1872-6259 10.1016/j.geoderma.2026.117890 282307331 https://www.sciencedirect.com/science/article/pii/S0016706126002181 1 02758e11-6ee0-11f1-98c5-001a4af901a5 https://dirros.openscience.si/Dokument.php?lang=slv&id=46050 RAZ_Leitao_Ricardo_2026.pdf RAZ_Leitao_Ricardo_2026.pdf 1 E45316B494166063FE7A11F8AC2CD412 0299de8fdfc66453b6ab77e0f0aadcf7fe04e02444c7caf9abc02dcd7bd90ebc 539b4b3e-6ee0-11f1-98c5-001a4af901a5 https://dirros.openscience.si/Dokument.php?lang=slv&id=46051 Institut Jožef Stefan 0 0 0