paper-with-me

Papers

NL2Scratch: An Executable Benchmark and Evaluation for Block-Based Programming

2026-06-20 · Heejin Do, Alexandre Ballenghien, Yang Wu, April Yi Wang arxiv

Block-based programming environments such as Scratch are widely used in early programming education, yet natural-language-to-code (NL2Code) research has focused primarily on text-based languages. Scratch programs are event-driven, visually compositional, and distributed across concurrent scripts, making conventional NL2Code assumptions and evaluation insufficient. We introduce NL2Scratch, an executable benchmark for natural-language-to-Scratch generation comprising 311,648 parser-valid NL--program pairs, whose program side is extracted from real Scratch projects and paired with semantically aligned NL descriptions. For reliable evaluation beyond surface overlap, we propose Semantic Alignment Consistency (SAC), an interpretable slot-level metric for measuring semantic agreement between descriptions and programs. With SAC, we construct a semantically validated pool of 23,594 examples, and a slot-balanced 800 diagnostic benchmark. Experiments across instruction-tuned and fine-tuned LLMs reveal a notable gap between lexical similarity and semantic alignment: models achieving token-level F1 above 0.93 often fail to attain perfect SAC, particularly on longer examples. Errors concentrate on operational slots like actions, conditions, and numeric arguments, exposing failure modes largely invisible under conventional metrics.

📄 PDF Abstract BibTeX arXiv:2606.22061

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

ScratchEval: Are GPT-4o Smarter than My Child? Evaluating Large Multimodal Models with Visual Programming Challenges

2024-11-28 · Rao Fu, Ziyang Luo, Hongzhan Lin, Zhen Ye 외

Recent advancements in large multimodal models (LMMs) have showcased impressive code generation capabilities, primarily evaluated through image-to-code benchmarks. However, these benchmarks are limited to specific visual…

Code Generation

ChatScratch: An AI-Augmented System Toward Autonomous Visual Programming Learning for Children Aged 6-12

2024-02-07 · Liuqing Chen, Shuhong Xiao, Yunnong Chen, Ruoyu Wu 외

As Computational Thinking (CT) continues to permeate younger age groups in K-12 education, established CT platforms such as Scratch face challenges in catering to these younger learners, particularly those in the element…

Image Generation

See, Plan, Snap: Evaluating Multimodal GUI Agents in Scratch

2026-02-11 · Xingyi Zhang, Yulei Ye, Kaifeng Huang, Wenhao Li 외 arxiv

Block-based programming environments such as Scratch play a central role in low-code education, yet evaluating the capabilities of AI agents to construct programs through Graphical User Interfaces (GUIs) remains underexp…

Robo-Blocks: Generative Scaffolding in End-User Design and Programming of Social Robots

2026-05-27 · Arissa J. Sato, Callie Y. Kim, Nathan Thomas White, Abhinav Maneesh 외 arxiv

Programming social robots is challenging for novice robot programmers due to required expertise in planning, interaction design, and programming. While large language models (LLMs) hold significant promise through code g…

Code Generation

RunBugRun -- An Executable Dataset for Automated Program Repair

2023-04-03 · Julian Aron Prenner, Romain Robbes

Recently, we can notice a transition to data-driven techniques in Automated Program Repair (APR), in particular towards deep neural networks. This entails training on hundreds of thousands or even millions of non-executa…

Program Repair