Papers by Jens Lemmens
In Benchmarks We Trust ... Or Not? (2025.emnlp-main)
Copied to clipboard
Ine Gevers, Victor De Marez, Jens Van Nooten, Jens Lemmens, Andriy Kosar, Ehsan Lotfi, Nikolay Banar, Pieter Fivez, Luna De Bruyne, Walter Daelemans
| Challenge: | Existing benchmarks for Large Language Models (LLMs) are inadequate and lack a clear solution. |
| Approach: | They propose checklists to cover all aspects of benchmarking issues, both for benchmark creation and usage. |
| Outcome: | The proposed checklists cover all aspects of benchmarking issues, both for benchmark creation and usage. |
CoNTACT: A Dutch COVID-19 Adapted BERT for Vaccine Hesitancy and Argumentation Detection (2022.coling-1)
Copied to clipboard
| Challenge: | CoNTACT is a Dutch language model adapted to the domain of COVID-19 tweets . a turbulent vaccine debate has emerged between advocates and opponents of vaccines - a polarization that will continue to influence future views on vaccines. |
| Approach: | They propose a Dutch language model adapted to the domain of COVID-19 tweets . they use 2.8M Dutch COVId-19 related tweets posted in 2021 to test the model . |
| Outcome: | The proposed model shows statistically significant gains over RobBERT on two tasks. |