[2601.02589] FlowPlan-G2P: A Structured Generation Framework for Transforming Scientific Papers into Patent Descriptions

-->

Computer Science > Computation and Language

arXiv:2601.02589 (cs)

[Submitted on 5 Jan 2026 (v1), last revised 23 May 2026 (this version, v4)]

Title:FlowPlan-G2P: A Structured Generation Framework for Transforming Scientific Papers into Patent Descriptions

Authors:Kris W Pan, Yongmin Yoo<br>View a PDF of the paper titled FlowPlan-G2P: A Structured Generation Framework for Transforming Scientific Papers into Patent Descriptions, by Kris W Pan and 1 other authors

View PDF<br>HTML (experimental)

Abstract:Generating patent descriptions from scientific papers is challenging due to fundamental rhetorical and structural disparities between the two genres. Existing approaches treat this as surface-level rewriting, failing to capture the hierarchical reasoning and statutory constraints inherent in patent drafting. We propose FlowPlan-G2P, a graph-mediated generation framework that decomposes this transformation into three stages: (1) Concept Graph Induction, extracting technical entities and functional dependencies into a directed graph; (2) Section-level Planning, partitioning the graph into coherent subgraphs aligned with canonical patent sections; and (3) Graph-Conditioned Generation, synthesizing legally compliant paragraphs conditioned on section-specific subgraphs. Experiments on expert-validated benchmarks reveal that standard NLG metrics systematically favor legally non-compliant outputs over valid patent descriptions, motivating our domain-specific evaluation. Under this evaluation, FlowPlan-G2P with an open-weight backbone consistently outperforms vanilla proprietary models, demonstrating that structured decomposition is a stronger determinant of quality than model scale.

Subjects:

Computation and Language (cs.CL); Artificial Intelligence (cs.AI)

Cite as:<br>arXiv:2601.02589 [cs.CL]

(or<br>arXiv:2601.02589v4 [cs.CL] for this version)

https://doi.org/10.48550/arXiv.2601.02589

Focus to learn more

arXiv-issued DOI via DataCite

Submission history<br>From: Yoo Yongmin [view email]<br>[v1]<br>Mon, 5 Jan 2026 22:40:15 UTC (10,029 KB)

[v2]<br>Tue, 14 Apr 2026 08:59:16 UTC (1,358 KB)

[v3]<br>Wed, 13 May 2026 12:15:30 UTC (1,358 KB)

[v4]<br>Sat, 23 May 2026 02:45:09 UTC (7,092 KB)

Full-text links:<br>Access Paper:

View a PDF of the paper titled FlowPlan-G2P: A Structured Generation Framework for Transforming Scientific Papers into Patent Descriptions, by Kris W Pan and 1 other authors<br>View PDF<br>HTML (experimental)<br>TeX Source

view license

Current browse context:

cs.CL

next >

new<br>recent<br>| 2026-01

Change to browse by:

cs<br>cs.AI

References & Citations

NASA ADS<br>Google Scholar

Semantic Scholar

export BibTeX citation<br>Loading...

BibTeX formatted citation

&times;

loading...

Data provided by:

Bookmark

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

Author

Venue

Institution

Topic

About arXivLabs

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs .

Which authors of this paper are endorsers? |<br>Disable MathJax (What is MathJax?)