Cross-lingual emotion detection allows us to analyze global trends, public
opinion, and social phenomena at scale. We participated in the Explainability
of Cross-lingual Emotion Detection (EXALT) shared task, achieving an F1-score
of 0.6046 on the evaluation set for the emotion detection sub-task. Our system
outperformed the baseline by more than 0.16 F1-score absolute, and ranked
second amongst competing systems. We conducted experiments using fine-tuning,
zero-shot learning, and few-shot learning for Large Language Model (LLM)-based
models as well as embedding-based BiLSTM and KNN for non-LLM-based techniques.
Additionally, we introduced two novel methods: the Multi-Iteration Agentic
Workflow and the Multi-Binary-Classifier Agentic Workflow. We found that
LLM-based approaches provided good performance on multilingual emotion
detection. Furthermore, ensembles combining all our experimented models yielded
higher F1-scores than any single approach alone.

我们参与了 Explainability of Cross-lingual Emotion Detection（EXALT）共享任务，在情感检测子任务的评估集上实现了 0.6046 的 F1 分数，超过基准模型 0.16 个 F1 分数，并在竞争系统中排名第二。我们通过使用 Fine-tuning、Zero-shot learning 和 Few-shot learning 方法在基于 Large Language Model（LLM）和非 LLM 的技术中，包括嵌入式的 BiLSTM 和 KNN 进行实验。此外，我们引入了两种新方法：多次迭代代理工作流和多二元分类器代理工作流。我们发现 LLM 方法对多语言情感检测提供了良好的性能。此外，将所有实验模型组合起来的集成模型比任何单一方法都有更高的 F1 分数。