Training-Free Character-Length Control in Summarization with Diffusion Language Models

Summarization with a fixed character length is important for tasks such as headline and article preview generation, where text must fit an exact space.

By Castle, Feldhus, Ebert +2Nov 4, 2026

Score████░░░░░░3.8

VerdictWorth a reader's time today.

Read the original PDF

Abstract

Summarization with a fixed character length is important for tasks such as headline and article preview generation, where text must fit an exact space. Autoregressive language models (LMs) struggle with precise character-length control: training-based methods require task-specific fine-tuning, while zero-shot prompting strategies achieve only approximate compliance. We propose DELTA (Diffusion Expected Length Targeting Algorithm), a training-free inference-time method for masked diffusion LMs that estimates expected character length at each denoising step and dynamically inserts or removes masked positions to steer toward a target length. DELTA requires no fine-tuning and is designed for off-the-shelf masked diffusion LMs. Across three summarization benchmarks, it reduces character-length errors by an order of magnitude compared to baselines while maintaining competitive summary quality in both automatic and human evaluation.

Steffen Castle, Nils Feldhus, Christopher Ebert, Leonhard Hennig, Sebastian Möller

The editor's rubric

Heuristic review

Leverage4 / 5: A general-purpose tool used across several fields (Adam, ResNet, LoRA, next-generation sequencing).; 24% of this desk’s rubric
Magnitude3 / 5: Large gain: roughly 2x, or a clear new state of the art on a hard, unsaturated problem.; 18% of this desk’s rubric
Evidence3 / 5: Solid: multiple benchmarks or cohorts, ablations, fair baselines, released code or data.; 14% of this desk’s rubric
Novelty3 / 5: A genuinely new approach to an open problem.; 16% of this desk’s rubric
Trajectory3 / 5: A clear path to scale.; 18% of this desk’s rubric
Stakes2 / 5: Benefits a professional community (practitioners, clinicians, engineers).; 10% of this desk’s rubric

Dimension	Level	Weight	What that level means
Leverage	████░4/5	24%	A general-purpose tool used across several fields (Adam, ResNet, LoRA, next-generation sequencing).
Magnitude	███░░3/5	18%	Large gain: roughly 2x, or a clear new state of the art on a hard, unsaturated problem.
Evidence	███░░3/5	14%	Solid: multiple benchmarks or cohorts, ablations, fair baselines, released code or data.
Novelty	███░░3/5	16%	A genuinely new approach to an open problem.
Trajectory	███░░3/5	18%	A clear path to scale.
Stakes	██░░░2/5	10%	Benefits a professional community (practitioners, clinicians, engineers).

Editor’s rationale

Heuristic triage from title and abstract text only, not a reading of the paper. Cues found: method (we propose); breadth (many tasks, zero/few-shot); gains (orders of magnitude); verification (multiple benchmarks, human evaluation); scale (orders of magnitude); stakes (general AI).

How the score was computed

rank-2026-10-18

Score████░░░░░░3.8

Score = 10 × (65% × adjusted merit / 10 + 25% × attention + 10% × freshness)

Desks place stronger verdicts first, then use this score to order work within the same verdict.

Merit: 6.3 / 10; Weighted rubric, evidence-gated.
Adjusted merit: 5.0 / 10; Shrunk toward the desk prior by editor confidence (46%).
Attention: 0%; Citations, upvotes, points, mentions.
Freshness: 56%; Half-life decay since publication.

No attention signals recorded yet.

The record

Reviewed by heuristic-v10 on Nov 5, 2026, 13:49 UTC. Paper type: method.
Categories: cs.CL
BRIEF, No.6 in the Artificial Intelligence edition of November 5, 2026.