Lev Kharlashkin ; Melany Macias ; Leo Huovinen ; Mika Hämäläinen - Predicting Sustainable Development Goals Using Course Descriptions -- from LLMs to Conventional Foundation Models

jdmdh:13127 - Journal of Data Mining & Digital Humanities, April 29, 2024, NLP4DH - https://doi.org/10.46298/jdmdh.13127
Predicting Sustainable Development Goals Using Course Descriptions -- from LLMs to Conventional Foundation ModelsArticle

Authors: Lev Kharlashkin ORCID; Melany Macias ; Leo Huovinen ; Mika Hämäläinen ORCID

We present our work on predicting United Nations sustainable development goals (SDG) for university courses. We use an LLM named PaLM 2 to generate training data given a noisy human-authored course description input as input.
We use this data to train several different smaller language models to predict SDGs for university courses. This work contributes to better university level adaptation of SDGs. The best performing model in our experiments was BART with an F1-score of 0.786.

Comment: 3 figures, 2 tables

https://doi.org/10.46298/jdmdh.13127
Source: arXiv.org:2402.16420
Volume: NLP4DH
Published on: April 29, 2024
Accepted on: April 9, 2024
Submitted on: February 27, 2024
Keywords: Computer Science - Computation and Language
Licence: Attribution 4.0 International (CC BY 4.0)

2 Documents citing this article

Share and export

Consultation statistics

This page has been seen 1355 times.
This article's PDF has been downloaded 588 times.