Pith. sign in

REVIEW 4 cited by

SVGEditBench: A Benchmark Dataset for Quantitative Assessment of LLM's SVG Editing Capabilities

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2404.13710 v1 pith:PMWMLVO2 submitted 2024-04-21 cs.CV

Kunato Nishina , Yusuke Matsui This is my paper
classification cs.CV
keywords svgeditbenchbenchmarkllmsabilitycodedataseteditediting
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Text-to-image models have shown progress in recent years. Along with this progress, generating vector graphics from text has also advanced. SVG is a popular format for vector graphics, and SVG represents a scene with XML text. Therefore, Large Language Models can directly process SVG code. Taking this into account, we focused on editing SVG with LLMs. For quantitative evaluation of LLMs' ability to edit SVG, we propose SVGEditBench. SVGEditBench is a benchmark for assessing the LLMs' ability to edit SVG code. We also show the GPT-4 and GPT-3.5 results when evaluated on the proposed benchmark. In the experiments, GPT-4 showed superior performance to GPT-3.5 both quantitatively and qualitatively. The dataset is available at https://github.com/mti-lab/SVGEditBench.

Discussion (0). Sign in to comment.

Forward citations

Cited by 4 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. DrawAI: Agentic Benchmark and Workflow for Making Raster Images Editable

    cs.CV 2026-08 conditional novelty 7.0 of 10

    A human-validated 39-criterion benchmark plus a parse-plan-reconstruct workflow for measuring and improving how multimodal agents convert raster images into editable vector artifacts.

  2. Vector-Bench: Can Models Surgically Edit SVG Code?

    cs.AI 2026-07 conditional novelty 6.0 of 10

    Only 2.35% of 1,360 model outputs pass Vector-Bench's three-gate SVG repair-and-preserve reward, and the best endpoint passes 15.0% despite 43.7% mean repair progress.

  3. Correspondence as Video: Test-Time Adaption on SAM2 for Reference Segmentation in the Wild

    cs.CV 2025-08 unverdicted novelty 6.0 of 10

    CAV-SAM reformulates reference segmentation as pseudo-video object segmentation using diffusion-based semantic transitions and test-time geometric alignment, claiming over 5% improvement over state-of-the-art.

  4. VectorEdits: A Dataset and Benchmark for Instruction-Based Editing of Vector Graphics

    cs.LG 2025-06 conditional novelty 5.0 of 10

    VectorEdits is a 271k-pair dataset and benchmark for text-guided vector image editing, and current LLMs fail to outperform a no-edit baseline.

Pith tools