Automating Research Synthesis with Domain-Specific Large Language Model Fine-Tuning

Checked 30 Sept 2026. Non-commercial or no-derivatives license: full text kept internally; only metadata and abstract are indexed and used.

The sources disagree. The gate chose the strictest class (red). A human review set it to yellow: “Applies to the submitted version (preprint) in an open repository (OpenAlex/Unpaywall, oa_status green), which is the copy this system uses; the version of record is under publisher terms (Crossref). Reviewed by Fredrik 2026-09-30. Corrected 2026-10-01: the earlier note called it the accepted manuscript; Unpaywall lists it as submittedVersion.”

This research pioneers the use of fine-tuned Large Language Models (LLMs) to automate Systematic Literature Reviews (SLRs), presenting a significant and novel contribution in integrating AI to enhance academic research methodologies. Our study employed advanced fine-tuning methodologies on open sourced LLMs, applying textual data mining techniques to automate the knowledge discovery and synthesis phases of an SLR process, thus demonstrating a practical and efficient approach for extracting and analyzing high-quality information from large academic datasets. The results maintained high fidelity in factual accuracy in LLM responses, and were validated through the replication of an existing PRISMA-conforming SLR. Our research proposed solutions for mitigating LLM hallucination and proposed mechanisms for tracking LLM responses to their sources of information, thus demonstrating how this approach can meet the rigorous demands of scholarly research. The findings ultimately confirmed the potential of fine-tuned LLMs in streamlining various labor-intensive processes of conducting literature reviews. As a scalable proof-of-concept, this study highlights the broad applicability of our approach across multiple research domains. The potential demonstrated here advocates for updates to PRISMA reporting guidelines, incorporating AI-driven processes to ensure methodological transparency and reliability in future SLRs. This study broadens the appeal of AI-enhanced tools across various academic and research fields, demonstrating how to conduct comprehensive and accurate literature reviews with more efficiency in the face of ever-increasing volumes of academic studies while maintaining high standards.

• Hallucination and factual inaccuracy are the shared motivation for grounding LLMs across this body of work: Akari et al. 2023 blame errors on sole reliance on parametric knowledge, Matsumoto et al. 2024 cite hallucinated or irrelevant content and noisy data, and Sušnjak et al. 2025 explicitly design hallucination-mitigation solutions. Trace →
• Sušnjak et al. 2025 show that fine-tuned open-source LLMs can automate the knowledge-discovery and synthesis phases of systematic literature reviews while maintaining high factual fidelity, validated through the replication of an existing PRISMA-conforming review. Trace →
• Traceability of generated text back to its sources emerges as a shared reliability mechanism: Sušnjak et al. 2025 propose tracking LLM responses to their information sources, and Matsumoto et al. 2024 envision medical deployments of KRAGEN providing personalized, evidence-based solutions with full transparency of reasoning and knowledge. Trace →

• RAG reliability and evaluation