EdiText: Controllable Coarse-to-Fine Text Editing with Diffusion Language Models
Che Hyun Lee, Heeseung Kim, Jiheum Yeom, Sungroh Yoon
Abstract
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.
BibTeX
@inproceedings{lee-etal-2025-editext,
title = "{E}di{T}ext: Controllable Coarse-to-Fine Text Editing with Diffusion Language Models",
author = "Lee, Che Hyun and
Kim, Heeseung and
Yeom, Jiheum and
Yoon, Sungroh",
editor = "Che, Wanxiang and
Nabende, Joyce and
Shutova, Ekaterina and
Pilehvar, Mohammad Taher",
booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.acl-long.1111/",
doi = "10.18653/v1/2025.acl-long.1111",
pages = "22798--22815",
ISBN = "979-8-89176-251-0"
}