Personalized Text Generation with Fine-Grained Linguistic Control

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Alhafni, Bashar, Kulkarni, Vivek, Kumar, Dhruv, Raheja, Vipul
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916117689139200
author Alhafni, Bashar
Kulkarni, Vivek
Kumar, Dhruv
Raheja, Vipul
author_facet Alhafni, Bashar
Kulkarni, Vivek
Kumar, Dhruv
Raheja, Vipul
contents As the text generation capabilities of large language models become increasingly prominent, recent studies have focused on controlling particular aspects of the generated text to make it more personalized. However, most research on controllable text generation focuses on controlling the content or modeling specific high-level/coarse-grained attributes that reflect authors' writing styles, such as formality, domain, or sentiment. In this paper, we focus on controlling fine-grained attributes spanning multiple linguistic dimensions, such as lexical and syntactic attributes. We introduce a novel benchmark to train generative models and evaluate their ability to generate personalized text based on multiple fine-grained linguistic attributes. We systematically investigate the performance of various large language models on our benchmark and draw insights from the factors that impact their performance. We make our code, data, and pretrained models publicly available.
format Preprint
id arxiv_https___arxiv_org_abs_2402_04914
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Personalized Text Generation with Fine-Grained Linguistic Control
Alhafni, Bashar
Kulkarni, Vivek
Kumar, Dhruv
Raheja, Vipul
Computation and Language
As the text generation capabilities of large language models become increasingly prominent, recent studies have focused on controlling particular aspects of the generated text to make it more personalized. However, most research on controllable text generation focuses on controlling the content or modeling specific high-level/coarse-grained attributes that reflect authors' writing styles, such as formality, domain, or sentiment. In this paper, we focus on controlling fine-grained attributes spanning multiple linguistic dimensions, such as lexical and syntactic attributes. We introduce a novel benchmark to train generative models and evaluate their ability to generate personalized text based on multiple fine-grained linguistic attributes. We systematically investigate the performance of various large language models on our benchmark and draw insights from the factors that impact their performance. We make our code, data, and pretrained models publicly available.
title Personalized Text Generation with Fine-Grained Linguistic Control
topic Computation and Language
url https://arxiv.org/abs/2402.04914