Towards Few-Shot Identification of Morality Frames using In-Context Learning
This work addresses data scarcity in NLP for specialized annotation tasks, offering a cost-effective alternative to expensive human annotation for researchers in psycho-linguistics and related fields, though it is incremental as it applies existing in-context learning methods to a new domain.
The paper tackled the problem of few-shot identification of morality frames in text, a nuanced socio-linguistic concept, by proposing prompting-based approaches using pre-trained Large Language Models, achieving promising results compared to few-shot RoBERTa.
Data scarcity is a common problem in NLP, especially when the annotation pertains to nuanced socio-linguistic concepts that require specialized knowledge. As a result, few-shot identification of these concepts is desirable. Few-shot in-context learning using pre-trained Large Language Models (LLMs) has been recently applied successfully in many NLP tasks. In this paper, we study few-shot identification of a psycho-linguistic concept, Morality Frames (Roy et al., 2021), using LLMs. Morality frames are a representation framework that provides a holistic view of the moral sentiment expressed in text, identifying the relevant moral foundation (Haidt and Graham, 2007) and at a finer level of granularity, the moral sentiment expressed towards the entities mentioned in the text. Previous studies relied on human annotation to identify morality frames in text which is expensive. In this paper, we propose prompting-based approaches using pretrained Large Language Models for identification of morality frames, relying only on few-shot exemplars. We compare our models' performance with few-shot RoBERTa and found promising results.