2025
ACL
ACL 2025
EdiText: Controllable Coarse-to-Fine Text Editing with Diffusion Language Models
Abstract
AbstractWe 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.
🌉
Interdisciplinary Bridge
— Machine Learning and Natural Language Processing
🧭
Keyword Pioneer
— diffusion language model
🐝
Cross-Pollinator
— Artificial Intelligence, Machine Learning, Natural Language Processing
Authors
Topics
Machine Learning > Core Methods > Representation Learning
Deep Learning > Models > Diffusion Models
Natural Language Processing > Generation > Text Generation
Artificial Intelligence > Core AI > Large Language Models
Natural Language Processing > Applications > Text Generation
Deep Learning > Learning Types > Generative Models
Artificial Intelligence > Core AI > Natural Language Generation