@inproceedings{he-etal-2025-flow2code,
title = "{F}low2{C}ode: Evaluating Large Language Models for Flowchart-based Code Generation Capability",
author = "He, Mengliang and
Zeng, Jiayi and
Jiang, Yankai and
Zhang, Wei and
Liu, Zeming and
Shi, Xiaoming and
Zhou, Aimin",
editor = "Che, Wanxiang and
Nabende, Joyce and
Shutova, Ekaterina and
Pilehvar, Mohammad Taher",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2025",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.findings-acl.425/",
doi = "10.18653/v1/2025.findings-acl.425",
pages = "8124--8146",
ISBN = "979-8-89176-256-5",
abstract = "While large language models (LLMs) show promise in code generation, existing benchmarks neglect the flowchart-based code generation. To promote further research on flowchart-based code generation, this work presents Flow2Code, a novel benchmark for flowchart-based code generation evaluation. The evaluation dataset spans 15 programming languages and includes 5,622 code segments paired with 16,866 flowcharts of three types: code, UML, and pseudocode. Extensive experiments with 13 multimodal LLMs reveal that current LLMs can not generate code based on flowcharts perfectly. Besides, experiment results show that the supervised fine-tuning technique contributes greatly to the models' performance. The dataset will be publicly available."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="he-etal-2025-flow2code">
<titleInfo>
<title>Flow2Code: Evaluating Large Language Models for Flowchart-based Code Generation Capability</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mengliang</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiayi</namePart>
<namePart type="family">Zeng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yankai</namePart>
<namePart type="family">Jiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wei</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zeming</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaoming</namePart>
<namePart type="family">Shi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aimin</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2025</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wanxiang</namePart>
<namePart type="family">Che</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joyce</namePart>
<namePart type="family">Nabende</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Shutova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammad</namePart>
<namePart type="given">Taher</namePart>
<namePart type="family">Pilehvar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Vienna, Austria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-256-5</identifier>
</relatedItem>
<abstract>While large language models (LLMs) show promise in code generation, existing benchmarks neglect the flowchart-based code generation. To promote further research on flowchart-based code generation, this work presents Flow2Code, a novel benchmark for flowchart-based code generation evaluation. The evaluation dataset spans 15 programming languages and includes 5,622 code segments paired with 16,866 flowcharts of three types: code, UML, and pseudocode. Extensive experiments with 13 multimodal LLMs reveal that current LLMs can not generate code based on flowcharts perfectly. Besides, experiment results show that the supervised fine-tuning technique contributes greatly to the models’ performance. The dataset will be publicly available.</abstract>
<identifier type="citekey">he-etal-2025-flow2code</identifier>
<identifier type="doi">10.18653/v1/2025.findings-acl.425</identifier>
<location>
<url>https://aclanthology.org/2025.findings-acl.425/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>8124</start>
<end>8146</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Flow2Code: Evaluating Large Language Models for Flowchart-based Code Generation Capability
%A He, Mengliang
%A Zeng, Jiayi
%A Jiang, Yankai
%A Zhang, Wei
%A Liu, Zeming
%A Shi, Xiaoming
%A Zhou, Aimin
%Y Che, Wanxiang
%Y Nabende, Joyce
%Y Shutova, Ekaterina
%Y Pilehvar, Mohammad Taher
%S Findings of the Association for Computational Linguistics: ACL 2025
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-256-5
%F he-etal-2025-flow2code
%X While large language models (LLMs) show promise in code generation, existing benchmarks neglect the flowchart-based code generation. To promote further research on flowchart-based code generation, this work presents Flow2Code, a novel benchmark for flowchart-based code generation evaluation. The evaluation dataset spans 15 programming languages and includes 5,622 code segments paired with 16,866 flowcharts of three types: code, UML, and pseudocode. Extensive experiments with 13 multimodal LLMs reveal that current LLMs can not generate code based on flowcharts perfectly. Besides, experiment results show that the supervised fine-tuning technique contributes greatly to the models’ performance. The dataset will be publicly available.
%R 10.18653/v1/2025.findings-acl.425
%U https://aclanthology.org/2025.findings-acl.425/
%U https://doi.org/10.18653/v1/2025.findings-acl.425
%P 8124-8146
Markdown (Informal)
[Flow2Code: Evaluating Large Language Models for Flowchart-based Code Generation Capability](https://aclanthology.org/2025.findings-acl.425/) (He et al., Findings 2025)
ACL