(in Polish) Systemy sztucznej inteligencji w pracy badawczej 290-KO3-1SSZI
Study programme profile – general academic.
Mode of study – full-time.
Course type – compulsory.
Field and discipline of study – social sciences, legal studies.
Year of study/semester – Year 1/Semester 1.
Prerequisites – none.
Number of teaching hours: 5 hours of seminar.
Teaching methods – heuristic method, problem-based learning, moderated discussion.
ECTS credits – 1.
PhD student workload breakdown: participation in classes 5 hours, preparation for classes and assessment 20 hours. Total: 25 hours, which corresponds to 1 ECTS credit.
Quantitative indicators: student workload associated with classes requiring the direct involvement of the lecturer: 5 hours, corresponding to 0.2 ECTS credits; and the PhD student’s workload not requiring the direct involvement of the lecturer: 20 hours, corresponding to 0.8 ECTS credits.
Type of course
Mode
Course coordinators
Learning outcomes
SKILLS: graduates are able to:
SD_UU01 - plan a self-development process individually, using soft skills to improve the efficiency of the learning process
SD_UK03 - take part and initiate the scientific discourse using soft skills, formulate conclusions, and make coherent summaries
Assessment criteria
Seminar: Assessment is based on the completion of an assignment involving the preparation of a report on the use of artificial intelligence-based tools to conduct a literature review, followed by a critical analysis of the results.
Subject to the regulations in force, the University reserves the right to conduct the final assessment via electronic means of communication.
The use by a student of an artificial intelligence system to complete tasks during remote asynchronous classes is permitted only to the extent and in accordance with the rules set out in Order No. 31 of the Rector of the University of Białystok dated 11 April 2025 on the use of artificial intelligence systems in the educational process at the University of Białystok. The use of an artificial intelligence system does not exempt the student from responsibility for the accuracy of the information and data used in their work.
Bibliography
Key literature:
Bolanos, F., Salatino, A., Osborne, F., & Motta, E. (2024). Artificial intelligence for literature reviews: Opportunities and challenges. Artificial Intelligence Review, 57(9), Article 259. https://doi.org/10.1007/s10462-024-10902-3
Han, B., Sušnjak, T., & Mathrani, A. (2024). Automating systematic literature reviews with retrieval-augmented generation: A comprehensive overview. Applied Sciences, 14(19), Article 9103. https://doi.org/10.3390/app14199103
Scherbakov, D., Hubig, N., Jansari, V., Bakumenko, A., & Lenert, L. A. (2025). The emergence of large language models as tools in literature reviews: A large language model-assisted systematic review. Journal of the American Medical Informatics Association, 32. https://doi.org/10.1093/jamia/ocaf063
Sušnjak, T. (2023). PRISMA-DFLLM: An extension of PRISMA for systematic literature reviews using domain-specific finetuned large language models [Preprint]. arXiv. https://doi.org/10.48550/arXiv.2306.14905
Supplementary literature
Liu, C., et al. (2025). A vision for auto research with LLM agents [Preprint]. arXiv. https://doi.org/10.48550/arXiv.2504.18765
Mikriukov, A., et al. (2025). AI tools for automating systematic literature reviews. In Proceedings of the 2025 International Conference on Software Engineering and Computer Applications. https://doi.org/10.1145/3747912.3747962
Rouzrokh, P., & Shariatnia, M. (2025). LatteReview: A multi-agent framework for systematic review automation using large language models [Preprint]. arXiv. https://doi.org/10.48550/arXiv.2501.05468
Saied, M., et al. (2024). AI in literature reviews: A survey of current and emerging methods. In 2024 International Mobile, Intelligent, and Ubiquitous Computing Conference (MIUCC). https://doi.org/10.1109/MIUCC62295.2024.10783597
Sami, M. A., et al. (2024). System for systematic literature review using multiple AI agents: Concept and an empirical evaluation [Preprint]. arXiv. https://doi.org/10.48550/arXiv.2403.08399
Zhao, W., & Mahmoud, Q. H. (2024). Evaluating the efficacy of large language models in automating academic peer reviews. In 2024 International Conference on Machine Learning and Applications (ICMLA). https://doi.org/10.1109/ICMLA61862.2024.00187
Additional information
Additional information (registration calendar, class conductors, localization and schedules of classes), might be available in the USOSweb system: