用集成方法检测社交媒体中的科学言论，准确率达86.1%
DS@GT at CheckThat! 2025: Ensemble Methods for Detection of Scientific Discourse on Social Media
- 融合微调Transformer与大模型少样本提示的集成策略
- 在多分类任务中取得0.8611的宏平均F1分数
- 适合关注虚假科学信息检测的研究者和实践者
本文为CLEF 2025 CheckThat!任务4a中DS@GT团队的参赛成果，针对社交媒体上的科学话语检测任务，判断推文是否包含科学主张、引用研究或提及科学实体（如大学、科学家）。我们探索了三种建模方法：Transformer微调、大模型少样本提示，以及基于前期实验设计的集成模型。最终在竞赛中位列第7，宏平均F1得分为0.8611，优于DeBERTaV3基线（0.8375）。代码已开源于https://github.com/dsgt-arc/checkthat-2025-swd/tree/main/subtask-4a。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。