English

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

Computation and Language 2025-06-03 v2 Machine Learning

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.

Keywords

Cite

@article{arxiv.2502.19765,
  title  = {EdiText: Controllable Coarse-to-Fine Text Editing with Diffusion Language Models},
  author = {Che Hyun Lee and Heeseung Kim and Jiheum Yeom and Sungroh Yoon},
  journal= {arXiv preprint arXiv:2502.19765},
  year   = {2025}
}

Comments

ACL 2025

R2 v1 2026-06-28T21:59:39.244Z