Are Large Language Models Actually Good at Text Style Transfer?

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Mukherjee, Sourabrata, Ojha, Atul Kr., Dušek, Ondřej
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866913481577463808
author Mukherjee, Sourabrata
Ojha, Atul Kr.
Dušek, Ondřej
author_facet Mukherjee, Sourabrata
Ojha, Atul Kr.
Dušek, Ondřej
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2406_05885
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Are Large Language Models Actually Good at Text Style Transfer?
Mukherjee, Sourabrata
Ojha, Atul Kr.
Dušek, Ondřej
Computation and Language
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.
title Are Large Language Models Actually Good at Text Style Transfer?
topic Computation and Language
url https://arxiv.org/abs/2406.05885