Empaths at SemEval-2025 Task 11: Retrieval-Augmented Approach to Perceived Emotions Prediction

TL;DR

This paper presents EmoRAG, a retrieval-augmented, ensemble-based system for multi-label emotion detection in text, achieving competitive results with improved efficiency and simplicity for SemEval-2025 Task 11.

Contribution

Introduces EmoRAG, a retrieval-augmented ensemble approach that predicts perceived emotions without additional training, enhancing scalability and ease of implementation.

Findings

Achieves performance comparable to top systems

Does not require additional model training

Offers a more efficient and scalable solution

Abstract

This paper describes EmoRAG, a system designed to detect perceived emotions in text for SemEval-2025 Task 11, Subtask A: Multi-label Emotion Detection. We focus on predicting the perceived emotions of the speaker from a given text snippet, labeling it with emotions such as joy, sadness, fear, anger, surprise, and disgust. Our approach does not require additional model training and only uses an ensemble of models to predict emotions. EmoRAG achieves results comparable to the best performing systems, while being more efficient, scalable, and easier to implement.