Year: 2025
Type: dissertation
Abstract: Large Language Models (LLM) are Artificial Intelligence (AI) models that can be fine-tuned for specific tasks. They can be used for Information Extraction (IE), a domain of Natural Language Processing (NLP), that aims to extract information from unstructured text and convert it into structured, machine-readable data. Using LLMs for IE allows for more accurate and less time-consuming extraction. For materials science using LLMs for IE enables a more automated extraction that can be used with Materials Science Databases, that store diverse data on different materials. With these tools materials science research can go towards a new era with data-driven studies. Using LLMs does have its challenges with hallucinations, environmental costs and transparency issues.
Source: UTUPub (University of Turku)
Author: Heino, Tiia
Language: English
Topic: Topic Modeling
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W7127243281
