SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2502.19765 · ACL · 2025

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

Sungroh Yoon, Heeseung Kim, Che Lee, Jiheum Yeom

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 8 functions out of this paper's own repositories and ran 7 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
zacharyhorvitz/ParaGuide — 7 of 8
FunctionStatusWhere it lives
apply_controlling_drift Ran zacharyhorvitz/ParaGuide/inference/diffusion_utils.py
pointer only (licence: NONE) · get_code("203f9667d8ada53a")
get_lr Ran zacharyhorvitz/ParaGuide/inference/diffusion_utils.py
pointer only (licence: NONE) · get_code("7ba6cd28cab4cdbd")
get_lr_semantic Ran zacharyhorvitz/ParaGuide/inference/diffusion_utils.py
pointer only (licence: NONE) · get_code("6fa1cb457e67473c")
get_time_variables_new_schedule Ran zacharyhorvitz/ParaGuide/inference/diffusion_utils.py
pointer only (licence: NONE) · get_code("728665bbd0418094")
get_time_variables_old_schedule Ran zacharyhorvitz/ParaGuide/inference/diffusion_utils.py
pointer only (licence: NONE) · get_code("41efcaf3a530a190")
logits_sampling_projection Ran zacharyhorvitz/ParaGuide/inference/diffusion_utils.py
pointer only (licence: NONE) · get_code("b1697e6aab49ae27")
run_model Ran zacharyhorvitz/ParaGuide/inference/diffusion_utils.py
pointer only (licence: NONE) · get_code("ebaece4b6551890a")
decode Not yet run zacharyhorvitz/ParaGuide/inference/diffusion_utils.py
pointer only (licence: NONE) · get_code("662fc3cfb477b4bd")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

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 selfconditioning, 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.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2502.19765")
get_code_for_paper("2502.19765")
have("2502.19765")

Connect an agent — have() is free.