538
v1v2 (latest)

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

Annual Meeting of the Association for Computational Linguistics (ACL), 2025
Main:9 Pages
6 Figures
Bibliography:3 Pages
9 Tables
Appendix:6 Pages
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.

View on arXiv
Comments on this paper