EdiText: Controllable Coarse-to-Fine Text Editing with Diffusion Language Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Lee, Che Hyun, Kim, Heeseung, Yeom, Jiheum, Yoon, Sungroh
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910979359506432
author Lee, Che Hyun
Kim, Heeseung
Yeom, Jiheum
Yoon, Sungroh
author_facet Lee, Che Hyun
Kim, Heeseung
Yeom, Jiheum
Yoon, Sungroh
contents We propose EdiText, a controllable text editing method that modifies the reference text to desired attributes at various scales. We integrate an SDEdit-based editing technique that allows for broad adjustments in the degree of text editing. Additionally, we introduce a novel fine-level editing method based on self-conditioning, which allows subtle control of reference text. While being capable of editing on its own, this fine-grained method, integrated with the SDEdit approach, enables EdiText to make precise adjustments within the desired range. EdiText demonstrates its controllability to robustly adjust reference text at a broad range of levels across various tasks, including toxicity control and sentiment control.
format Preprint
id arxiv_https___arxiv_org_abs_2502_19765
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle EdiText: Controllable Coarse-to-Fine Text Editing with Diffusion Language Models
Lee, Che Hyun
Kim, Heeseung
Yeom, Jiheum
Yoon, Sungroh
Computation and Language
Machine Learning
We propose EdiText, a controllable text editing method that modifies the reference text to desired attributes at various scales. We integrate an SDEdit-based editing technique that allows for broad adjustments in the degree of text editing. Additionally, we introduce a novel fine-level editing method based on self-conditioning, which allows subtle control of reference text. While being capable of editing on its own, this fine-grained method, integrated with the SDEdit approach, enables EdiText to make precise adjustments within the desired range. EdiText demonstrates its controllability to robustly adjust reference text at a broad range of levels across various tasks, including toxicity control and sentiment control.
title EdiText: Controllable Coarse-to-Fine Text Editing with Diffusion Language Models
topic Computation and Language
Machine Learning
url https://arxiv.org/abs/2502.19765