Are Large Language Models Actually Good at Text Style Transfer?
This work addresses the problem of effective text style transfer for multilingual applications, highlighting the need for dedicated resources, but it is incremental as it builds on existing LLM methods.
The paper analyzed large language models (LLMs) for text style transfer across English, Hindi, and Bengali, finding that prompted LLMs performed well only in English, but finetuning significantly improved results to match previous state-of-the-art.
We analyze the performance of large language models (LLMs) on Text Style Transfer (TST), specifically focusing on sentiment transfer and text detoxification across three languages: English, Hindi, and Bengali. Text Style Transfer involves modifying the linguistic style of a text while preserving its core content. We evaluate the capabilities of pre-trained LLMs using zero-shot and few-shot prompting as well as parameter-efficient finetuning on publicly available datasets. Our evaluation using automatic metrics, GPT-4 and human evaluations reveals that while some prompted LLMs perform well in English, their performance in on other languages (Hindi, Bengali) remains average. However, finetuning significantly improves results compared to zero-shot and few-shot prompting, making them comparable to previous state-of-the-art. This underscores the necessity of dedicated datasets and specialized models for effective TST.