stEELlm: An LLM for Generating Semantic Annotations of Tabular Data
Year: 2025
Type: article
Abstract: The capabilities of Large Language Models (LLMs) represent a pivotal step in transforming how we manage and interact with information and data. We witness an increasingly pervasive use of such models in various computational tasks. In some preliminary works, attempts to integrate Knowledge Graphs and LLMs can be identified, in particular, to perform the classic tasks related to the construction of Knowledge Graphs through semantic annotation of texts. Nowadays, tables are widely used and play a crucial role in creating, organising and sharing information that could be used to produce factual knowledge to be integrated into a Knowledge Graph. However, table-to-KG techniques through LLM have not been extensively investigated. This article presents stEELlm, an innovative Semantic Table Interpretation approach obtained by fine-tuning the Mixtral 8x7B model. Conducted experiments demonstrate the capabilities of our model to successfully create semantic annotations of heterogeneous datasets, a scenario where classic approaches based on heuristics tend to fail.
DOI: 10.1145/3719206
Authors: Marco Cremaschi, Fabio D’Adda, Andrea Maurino
Institution: University of Milano-Bicocca
Language: English
Topic: Topic Modeling
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
OpenAlex ID: W4407839089