Work

Evaluating the Impact of Adapter-Based Fine-Tuning on Structured Parsing Performance in Large Language Models

Year: 2026

Type: article

Abstract: Recent advances in large language models (LLMs) highlight two dominant strategies for performance improvement: prompt engineering and fine-tuning. While prompt design can significantly influence model output, it remains uncertain whether lightweight fine-tuning methods, such as adapter-based training, offer meaningful advantages for structured, domain-specific tasks. This study builds on prior research comparing three prompting strategies for natural-language command parsing into JSON schemas. Expanding that framework, the current work investigates how adapter-based fine-tuning, where most model parameters are frozen and only small adapter modules are trained, affects model accuracy and consistency. The experiment uses the same controlled shopping-cart parsing task and dataset of 12,000 synthetic commands to ensure direct comparability. Results quantify the trade-off between computational cost and performance gains, offering evidence-based insights into whether fine-tuning is a justified investment compared to advanced prompt engineering. The contribution of this study is a clear, empirical framework for deciding when fine-tuning meaningfully enhances LLM utility in applied natural-language understanding.

Source: Machine Learning and Knowledge Extraction

DOI: 10.3390/make8050138

Authors: Ratomir Karlović, Luka Sever, Sandi Baressi Šegota, Vedran Mrzljak, Ivan Lorencin

Institutions: Juraj Dobrila University of Pula, University of Rijeka

Language: English

Topic: Topic Modeling

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: gold

Estimated APC paid: $2,172

Funder: NextGenerationEU