20.500.12556/DiRROS-28309 FuDoBa fusing document and knowledge graph based representations with Bayesian optimisation FuDoBa: fusing document and knowledge graph based representations with Bayesian optimisation Building on the success of large language models (LLMs), LLM-based representations have dominated the document representation landscape, achieving strong performance on document embedding benchmarks. However, high-dimensional, computationally expensive LLM embeddings can be too generic or inefficient for domain-specific and resource-scarce applications. To address these limitations, we introduce FuDoBa—a Bayesian optimisation-based representation learning method that integrates LLM embeddings with domain-specific structured knowledge, sourced both locally and from external repositories such as WikiData. This fusion produces low-dimensional, task-relevant representations while reducing training complexity and yielding interpretable early-fusion weights for improved classification performance. We demonstrate the effectiveness of our approach on six datasets across two domains, showing that when paired with robust AutoML-based classifiers, our method performs on par with, or surpasses, proprietary LLM-only embedding baselines, while offering modality-wise interpretability and a smaller dimensional footprint. document classification Bayesian optimisation representation learning knowledge graphs razvrščanje dokumentov optimizacija grafi znanja true false true Springer Nature Švica Angleški jezik Slovenski jezik © The Author(s) 2026 Neznano 2026-03-13 13:11:15 2026-03-13 13:11:15 2026-03-14 04:25:57 0000-00-00 00:00:00 2026 0 0 Nasl. z nasl. zaslona; Soavtorja iz Slovenije: Senja Pollak, Blaž Škrlj; Opis vira z dne 13. 3. 2026; str. 1-39 Vol. 115, article no. 61 6 Mar. 2026 0000-00-00 Zaloznikova Objavljeno NiDoloceno 2025-04-23 2026-02-02 2026-03-06 004.8 1573-0565 10.1007/s10994-026-07008-y 271609091 https://link.springer.com/article/10.1007/s10994-026-07008-y 1 be06d08a-1ed5-11f1-acf8-001a4af901a5 https://dirros.openscience.si/Dokument.php?lang=slv&id=41801 RAZ_Koloski_Boshko_2026.pdf RAZ_Koloski_Boshko_2026.pdf 1 9BB8D0EAE48F39924BFB52DCFE589268 1efb91f6191563d1e44c976a239fb7a2f64cb75b1c273caf186bd2523decc01b 893678cc-1ed6-11f1-acf8-001a4af901a5 https://dirros.openscience.si/Dokument.php?lang=slv&id=41802 Institut Jožef Stefan 0 0 0