Customising General Large Language Models for Specialised Emotion Recognition Tasks
This work addresses the need for effective emotion recognition in natural language processing, though it is incremental as it applies existing adaptation techniques to a known LLM.
The paper tackles the problem of adapting large language models (LLMs) for specialized emotion recognition tasks, showing that customized LLMs using deep prompt tuning and low-rank adaptation outperform state-of-the-art specialized deep models on six datasets.
The advent of large language models (LLMs) has gained tremendous attention over the past year. Previous studies have shown the astonishing performance of LLMs not only in other tasks but also in emotion recognition in terms of accuracy, universality, explanation, robustness, few/zero-shot learning, and others. Leveraging the capability of LLMs inevitably becomes an essential solution for emotion recognition. To this end, we further comprehensively investigate how LLMs perform in linguistic emotion recognition if we concentrate on this specific task. Specifically, we exemplify a publicly available and widely used LLM -- Chat General Language Model, and customise it for our target by using two different modal adaptation techniques, i.e., deep prompt tuning and low-rank adaptation. The experimental results obtained on six widely used datasets present that the adapted LLM can easily outperform other state-of-the-art but specialised deep models. This indicates the strong transferability and feasibility of LLMs in the field of emotion recognition.