LLM‐Based Scientific Assistants for Knowledge Extraction: Which Design Choices Matter?
Advanced Intelligent Discovery · 21.04.2026
DOI: 10.1002/aidi.202500197 ↗Kurz gefasst
Fachartikel in der Zeitschrift Advanced Intelligent Discovery, online erschienen am 21.04.2026. Verfasst von David Exler und 7 weiteren Autor:innen. Die Arbeit nennt 93 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Large Language Model chatbots have gained significant popularity, offering knowledge to support specialists in diverse fields. However, adapting models to specific use cases and specialized domains presents considerable challenges. Hence, we introduce the LLM Playground, a comprehensive approach to optimizing LLMs for specialist applications with respect to their accuracy in answering domain‐specific questions, addressing the limitations of unmodified models. The utilized optimization techniques begin with Prompt Engineering, advance to the integration of external knowledge, and culminate in complex reasoning strategies or self‐feedback loops. This paper introduces various architectures for scientific assistants, comprising individual enhancement techniques, both in isolation and in combination with others, designed to facilitate comparisons. To demonstrate the efficacy of the LLM Playground, a chemical chatbot is set up as a case study, and the optimization techniques are compared using ChemBench, an independent question–answer benchmark for the chemical domain, to measure its performance. By providing tested, ready‐to‐deploy architectures and clear use‐case guidance, this work helps researchers and practitioners leverage LLMs in domain‐specific applications. The insights and methodologies presented in this paper contribute to the growing body of knowledge on tailoring LLMs to meet the unique demands of specialized fields.
Zitieren
APA
Exler, D., Raimann, M., Münker, M., Rosin, M., Gómez, J. E. U., Niemeyer, C. M., Reischl, M., & Rettenberger, L. (2026). LLM‐Based Scientific Assistants for Knowledge Extraction: Which Design Choices Matter?. Advanced Intelligent Discovery. https://doi.org/10.1002/aidi.202500197
Vancouver
Exler D, Raimann M, Münker M, Rosin M, Gómez JEU, Niemeyer CM, et al. LLM‐Based Scientific Assistants for Knowledge Extraction: Which Design Choices Matter?. Advanced Intelligent Discovery. 2026. doi:10.1002/aidi.202500197
BibTeX
@article{Exler2026,
author = {Exler, David and Raimann, Manuel and Münker, Marc and Rosin, Maxim and Gómez, Joaquin E. Urrutia and Niemeyer, Christof M. and Reischl, Markus and Rettenberger, Luca},
title = {LLM‐Based Scientific Assistants for Knowledge Extraction: Which Design Choices Matter?},
journal = {Advanced Intelligent Discovery},
year = {2026},
doi = {10.1002/aidi.202500197}
}
EUVIMED