Predicting Sustainable Development Goals Using Course Descriptions -- from LLMs to Conventional Foundation Models
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866929450193518592 |
|---|---|
| author | Kharlashkin, Lev Macias, Melany Huovinen, Leo Hämäläinen, Mika |
| author_facet | Kharlashkin, Lev Macias, Melany Huovinen, Leo Hämäläinen, Mika |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_16420 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Predicting Sustainable Development Goals Using Course Descriptions -- from LLMs to Conventional Foundation Models Kharlashkin, Lev Macias, Melany Huovinen, Leo Hämäläinen, Mika Computation and Language 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. |
| title | Predicting Sustainable Development Goals Using Course Descriptions -- from LLMs to Conventional Foundation Models |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2402.16420 |