CSIRO-LT at SemEval-2025 Task 11: Adapting LLMs for Emotion Recognition for Multiple Languages

TL;DR

This paper explores adapting large language models for emotion recognition across multiple languages, focusing on fine-tuning strategies to improve accuracy in culturally nuanced emotional detection.

Contribution

It introduces effective task-adaptation strategies for multilingual emotion recognition, highlighting fine-tuning with LoRA as the most successful approach.

Findings

Fine-tuning multilingual LLMs with LoRA improves emotion recognition accuracy.

Language-specific fine-tuning outperforms other adaptation methods.

The approach effectively captures culturally nuanced emotional expressions.

Abstract

Detecting emotions across different languages is challenging due to the varied and culturally nuanced ways of emotional expressions. The \textit{Semeval 2025 Task 11: Bridging the Gap in Text-Based emotion} shared task was organised to investigate emotion recognition across different languages. The goal of the task is to implement an emotion recogniser that can identify the basic emotional states that general third-party observers would attribute to an author based on their written text snippet, along with the intensity of those emotions. We report our investigation of various task-adaptation strategies for LLMs in emotion recognition. We show that the most effective method for this task is to fine-tune a pre-trained multilingual LLM with LoRA setting separately for each language.