DELA: Learning Controllable Edits for Diffusion Language Models

Xinsong Feng; Chenan Wang; Leshu Tang; Johnny Liu; Dong Li; Da Li; Haipeng Chen

cs.AIOct 23, 2026

DELA: Learning Controllable Edits for Diffusion Language Models

Authors: Xinsong Feng, Chenan Wang, Leshu Tang, Johnny Liu, Dong Li, Da Li, Haipeng Chen

Organizations: Georgia Institute of Technology · William & Mary · UCLA · Yotta Labs

Abstract

Diffusion language models (DLMs) support bidirectional denoising and iterative refinement, but generation remains largely controlled by token-level masking schedules. This leaves draft-level refinement implicit and limits explicit control over when to insert missing content, delete redundant spans, revisit uncertain regions, or stop editing. We introduce Diffusion Editing Language Adapter (DELA), a plug-in framework that enables controllable draft refinement with a frozen DLM. DELA operates on clean, variable-length drafts using four explicit editing actions: Insert, Delete, Remask, and Stop. The controller determines when and where to edit the draft, while the frozen DLM fills masked regions through denoising, separating high-level edit control from token-level generation. A naive single-phase editor would be computationally expensive because arbitrary interior edits can disrupt prefix stability and limit reliable KV-cache reuse. To address this, DELA uses a two-phase decoding procedure: a fast, append-only drafting phase that supports KV-cache reuse, followed by a global refinement phase that enables targeted non-monotonic edits to the full draft. We train the controller using a staged curriculum that begins with learning local edit priors from synthetic recovery tasks and mined actions that improve draft quality. Subsequent stages refine edit selection through rollout-based outcome preferences and alignment with downstream task feedback. Experiments on mathematical reasoning and code generation show that DELA achieves gains of up to 5.5 percentage points over direct diffusion decoding while keeping the backbone frozen. DELA thus provides a modular approach to explicit draft-level control in diffusion language models.

Figures & tables

Figure 1: Overview of DELA. A learned edit controller operates on clean variable-length drafts and selects structural actions, while the frozen DLM realizes masked content through denoising. This design decouples high-level edit control from token-level lexical generation.

Figure 2: Two-phase editing in DELA. The fast drafting phase constructs an initial draft with append-only masked-block insertion and local remasking, enabling cache-friendly generation. The global refinement phase then unlocks the full action space to insert missing content, delete redundant spans, remask uncertain regions, or stop.

Method	GSM8K	MATH	HumanEval	MBPP
Direct	80.5	36.7	37.2	39.6
Editor-only	83.6 (+3.1)	37.9 (+1.2)	39.0 (+1.8)	41.4 (+1.8)
Editor+Selector	85.7 (+5.2)	39.3 (+2.6)	42.7 (+5.5)	43.6 (+4.0)
Oracle	86.3 (+5.8)	39.8 (+3.1)	43.9 (+6.7)	44.0 (+4.4)

Table 1: Main downstream performance with a frozen LLaDA-1.5 backbone. All entries are percentages; numbers in parentheses denote absolute gains over Direct .

Method	pass@1	NFE	Latency (s)
Direct	37.2	256	5.43
Fast-dLLM	38.4	87	1.72
Tolerator-style	38.4	275	5.46
ReMDM	38.4	512	10.61
DELA-REMASK	40.9	261	5.57
DELA	42.7	264	5.74

Table 2: Inference-time comparison on HumanEval using the same frozen LLaDA-1.5 backbone.

Configuration	# Correct	pass@1
Stage 1	18	11.0
Stage 1 + Stage 2	61	37.2
DELA-REMASK	67	40.9
DELA	70	42.7
Oracle	72	43.9

Table 3: Component analysis on HumanEval with the frozen LLaDA-1.5 backbone.

Appendix figures & tables10 assets

Supplementary material from the paper’s appendix.

Appendix

Hyperparameter	Value
Denoising backbone	LLaDA-1.5
Backbone update	Frozen
Denoising operator	$\mathcal{D}_{\tau}$
Initial draft length	$\texttt{gen\_length}=256$
Initial denoising iterations	$\texttt{steps}=256$
Initial block length	$\texttt{block\_length}=16$

Appendix

Table 4: Main implementation hyperparameters for DELA.

Experiment	GPUs	Trainable components
Stage 1: learning executable edit proposals	8 RTX PRO 6000	Proposal editor
Stage 2: learning which edits improve a draft	8 RTX PRO 6000	Proposal editor, selector
Stage 3: aligning edits with task success	8 RTX PRO 6000	Proposal editor, selector
Downstream evaluation	8 RTX PRO 6000	None

Appendix

Table 5: Compute resources used for DELA experiments.

Scope	Op acc.	Pos acc.	Op+Pos acc.	Len $\pm 1$	Len $\pm 2$	Joint $\pm 1$	Joint $\pm 2$	Exact joint
Overall	89.5	83.5	74.8	41.5	59.8	30.3	45.8	12.3
Insert	95.5	70.0	67.5	27.5	43.5	19.0	31.0	4.0
Delete	83.5	97.0	82.0	55.5	76.0	41.5	60.5	20.5

Appendix

Table 6: Stage 1 synthetic recovery diagnostics. The editor is evaluated on synthetic corrupted drafts and predicts the recovery action toward the clean target. These metrics measure whether the editor learns executable edit syntax, not whether the resulting policy improves downstream generation.

Policy	Mined-positive	Top-1 improves	Large gain	Avg. gain
Synthetic recovery only	38.3	50.0	14.8	0.0070
Final Stage 1 editor	84.4	87.5	57.8	0.0230

Appendix

Table 7: Stage 1 proposal diagnostics, averaged over two seeds. Large gain denotes

\Delta>0.02

. All entries except Avg. gain are percentages.

Policy	Avg. reward	Recovered (%)
Stage 1 editor-only	-0.1270	40.6
Stage 2 selector	-0.0250	63.5
Oracle over candidates	0.1002	79.7

Appendix

Table 8: Stage 2 selection diagnostics on 256 validation examples. Recovered is the percentage of examples recovered after the selected edit.

Method	pass@1	NFE	Latency (s)
Block size $=8$	37.8	256	5.09
Block size $=16$ ( Direct )	37.2	256	5.43
Block size $=32$	39.0	256	4.99
Block size $=64$	37.8	256	5.04
Block size $=256$	14.0	256	5.26
Random ordering ( $b=32$ )	22.6	256	5.13

Appendix

Table 9: Additional decoding comparisons on HumanEval. All methods use the same frozen LLaDA-1.5 backbone.

Setting	Value	# Correct
Selector margin $\gamma_{\mathrm{op}}$	$0$	70
	$0.1$	70
	$0.5$	69
	$\infty$	64
Refinement budget $T_{\max}$	$1$	68
	$2$	70

Appendix

Table 10: Sensitivity to the selector margin

\gamma_{\mathrm{op}}

and refinement budget

T_{\max}

on HumanEval.

Metric	All examples	Direct -failure subset
Examples receiving an edit	15 / 164 (9.1%)	13 / 103 (12.6%)
REMASK / INSERT / DELETE	24 / 2 / 1	18 / 1 / 1
Changed tokens per REMASK, median	9	9
Changed tokens per edited example, median	12	12
Changed-token fraction, median	6.3%	5.9%

Appendix

Table 11: Edit statistics on HumanEval. Draft-length and changed-token statistics are computed only over examples receiving at least one edit.

Configuration	Latency (s)	Query positions	Attention pairs
Without prefix cache	0.414	5,370	1.51M
With prefix cache	0.364	727	0.18M

Appendix

Table 12: Prefix-cache profiling for 256-token fast drafting with batch size one.

Procedure	Latency (s/sample)	Relative cost
Two-phase drafting and refinement	0.461	1.0 $\times$
Refinement after every block	0.823	1.8 $\times$
Forced edit after every block	2.466	5.4 $\times$

Appendix

Table 13: Cost of two-phase decoding compared with invoking global refinement throughout draft construction.

Diffusion Language Models

Diffusion language models generate and refine text through iterative denoising, enabling bidirectional context and parallel token updates.

See all 466 papers

Edit-Based Refinement for Parallel Masked Diffusion Language Models
May 10, 2026Houxing Ren, Mingjie Zhan, Zimu Lu +5Masked Diffusion Models Parallel Decoding
CUHK MMLab · SenseTime Research · Shenzhen Loop Area Institute +1
DiLaDiff: Distilled Latent-Augmented Diffusion for Language Modeling
May 22, 2026Jean-Marie Lemercier, Tomas Geffner, Karsten Kreis +3Diffusion Language Models Diffusion Language Model Distillation
NVIDIA
LED: Improving Masked Diffusion Language Models by Lookahead Editing
Oct 16, 2026Yuyan Zhou, Zeyuan Yang, Yuxuan Song +5Diffusion Language Model Decoding Masked Diffusion Models
Department of Computer Science and Engineering, The Hong Kong University of Science and Technology · ByteDance Seed · Institute for AI Industry Research (AIR), Tsinghua University +1

May 10, 2026J/K move · Enter open · S save

Edit-Based Refinement for Parallel Masked Diffusion Language Models

Houxing Ren, Mingjie Zhan, Zimu Lu, Ke Wang+4

CUHK MMLab · SenseTime Research · Shenzhen Loop Area Institute+1

Masked Diffusion Models Parallel Decoding Diffusion Language Model Decoding Diffusion Language Models Diffusion Model Inference Acceleration Text Generation+1

Open paper AskPDF arXiv

Masked diffusion language models enable parallel token generation and offer improved decoding efficiency over autoregressive models. However, their performance degrades significantly when generating multiple tokens simultaneously, due to a mismatch between token-level training objectives and joint sequence consistency. In this paper, we propose ME-DLM, an edit-based refinement framework that augments diffusion generation with lightweight post-editing steps. After producing an initial complete response, the model refines it through minimal edit operations, including replacement, deletion, and insertion, conditioned on the full sequence. Training supervision is derived from edit distance, providing a deterministic signal under a fixed canonicalization scheme for learning minimal corrections. This approach encourages sequence-level consistency through globally conditioned edits while preserving the efficiency benefits of parallel diffusion decoding. Extensive experiments demonstrate that ME-DLM improves the quality and robustness of multi-token parallel generation. In particular, when built upon LLaDA, our method achieves consistent gains of 11.6 points on HumanEval and 33.6 points on GSM8K while using one-eighth of the total diffusion steps. Code is available at https://github.com/renhouxing/ME-DLM.

Abstract

Diffusion Language Models

Explore similar work

Edit-Based Refinement for Parallel Masked Diffusion Language Models

DiLaDiff: Distilled Latent-Augmented Diffusion for Language Modeling

LED: Improving Masked Diffusion Language Models by Lookahead Editing