DS@GT at CheckThat! 2025: Ensemble Methods for Detection of Scientific Discourse on Social Media

TL;DR

This paper explores ensemble methods combining transformer finetuning and few-shot prompting of large language models to detect scientific discourse in social media tweets, achieving improved performance in a competitive task.

Contribution

Introduces a combined ensemble approach for scientific discourse detection on social media, outperforming baseline models in the CheckThat! 2025 competition.

Findings

Ensemble model achieved a macro F1 score of 0.8611.

Transformer finetuning and LLM prompting are effective for this task.

Code is publicly available for reproducibility.

Abstract

In this paper, we, as the DS@GT team for CLEF 2025 CheckThat! Task 4a Scientific Web Discourse Detection, present the methods we explored for this task. For this multiclass classification task, we determined if a tweet contained a scientific claim, a reference to a scientific study or publication, and/or mentions of scientific entities, such as a university or a scientist. We present 3 modeling approaches for this task: transformer finetuning, few-shot prompting of LLMs, and a combined ensemble model whose design was informed by earlier experiments. Our team placed 7th in the competition, achieving a macro-averaged F1 score of 0.8611, an improvement over the DeBERTaV3 baseline of 0.8375. Our code is available on Github at https://github.com/dsgt-arc/checkthat-2025-swd/tree/main/subtask-4a.