Saved in:
Bibliographic Details
Main Authors: Sun, Huashan, Wu, Yixiao, Ye, Yuhao, Yang, Yizhe, Li, Yinghao, Li, Jiawei, Gao, Yang
Format: Preprint
Published: 2023
Subjects:
Online Access:https://arxiv.org/abs/2311.08389
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910646999711744
author Sun, Huashan
Wu, Yixiao
Ye, Yuhao
Yang, Yizhe
Li, Yinghao
Li, Jiawei
Gao, Yang
author_facet Sun, Huashan
Wu, Yixiao
Ye, Yuhao
Yang, Yizhe
Li, Yinghao
Li, Jiawei
Gao, Yang
contents Language style is necessary for AI systems to understand and generate diverse human language accurately. However, previous text style transfer primarily focused on sentence-level data-driven approaches, limiting exploration of potential problems in large language models (LLMs) and the ability to meet complex application needs. To overcome these limitations, we introduce a novel task called Public-Speaking Style Transfer (PSST), which aims to simulate humans to transform passage-level, official texts into a public-speaking style. Grounded in the analysis of real-world data from a linguistic perspective, we decompose public-speaking style into key sub-styles to pose challenges and quantify the style modeling capability of LLMs. For such intricate text style transfer, we further propose a fine-grained evaluation framework to analyze the characteristics and identify the problems of stylized texts. Comprehensive experiments suggest that current LLMs struggle to generate public speaking texts that align with human preferences, primarily due to excessive stylization and loss of semantic information.
format Preprint
id arxiv_https___arxiv_org_abs_2311_08389
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle PSST: A Benchmark for Evaluation-driven Text Public-Speaking Style Transfer
Sun, Huashan
Wu, Yixiao
Ye, Yuhao
Yang, Yizhe
Li, Yinghao
Li, Jiawei
Gao, Yang
Computation and Language
Artificial Intelligence
I.2.7
Language style is necessary for AI systems to understand and generate diverse human language accurately. However, previous text style transfer primarily focused on sentence-level data-driven approaches, limiting exploration of potential problems in large language models (LLMs) and the ability to meet complex application needs. To overcome these limitations, we introduce a novel task called Public-Speaking Style Transfer (PSST), which aims to simulate humans to transform passage-level, official texts into a public-speaking style. Grounded in the analysis of real-world data from a linguistic perspective, we decompose public-speaking style into key sub-styles to pose challenges and quantify the style modeling capability of LLMs. For such intricate text style transfer, we further propose a fine-grained evaluation framework to analyze the characteristics and identify the problems of stylized texts. Comprehensive experiments suggest that current LLMs struggle to generate public speaking texts that align with human preferences, primarily due to excessive stylization and loss of semantic information.
title PSST: A Benchmark for Evaluation-driven Text Public-Speaking Style Transfer
topic Computation and Language
Artificial Intelligence
I.2.7
url https://arxiv.org/abs/2311.08389