A Matter of Representation: Towards Graph-Based Abstract Code Generation

• URL: http://arxiv.org/abs/2510.13163v1
• Date: Wed, 15 Oct 2025 05:26:36 GMT
• Title: A Matter of Representation: Towards Graph-Based Abstract Code Generation
• Authors: Nyx Iskandar, Hisham Bedri, Andy Tsen,
• Abstract summary: We propose and evaluate representations for graphs to enable high accuracy graph-based abstract code generation.<n>This work establishes the first steps towards representation learning for graph-based abstract code generation.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Most large language models (LLMs) today excel at generating raw, sequential code with minimal abstractions and custom structures. However, there has been little work on graph-based abstract code generation, where significant logic is encapsulated in predefined nodes and execution flow is determined by edges. This is relevant for visual programming languages, and in cases where raw source code is inaccessible to users and LLM training sets. In this work, we propose and evaluate JSON representations for graphs to enable high accuracy graph-based abstract code generation. We evaluate these representations on ScratchTest, a mini-benchmark based on our custom Python re-implementation of Scratch, which tests the LLM in code graph space. Our findings demonstrate that LLMs can indeed perform the aforementioned generation task in a single pass without relying on specialized or complex pipelines, given the correct graph representations. We also show that different representations induce significantly different accuracies, highlighting the instrumental role of representations in this generation task. All in all, this work establishes the first steps towards representation learning for graph-based abstract code generation.

Related papers

• Colorful Talks with Graphs: Human-Interpretable Graph Encodings for Large Language Models [12.496005049442319]
  Graph problems are fundamentally challenging for large language models (LLMs)<n>We introduce a human-interpretable structural encoding strategy for graph-to-text translation.<n>Our method enhances LLM performance especially on graph tasks that require reasoning over global graph structure.
  arXiv  Detail & Related papers  (2026-02-11T00:15:29Z)
• Semi-supervised Instruction Tuning for Large Language Models on Text-Attributed Graphs [62.544129365882014]
  We propose a novel Semi-supervised Instruction Tuning pipeline for Graph Learning, named SIT-Graph.<n> SIT-Graph is model-agnostic and can be seamlessly integrated into any graph instruction tuning method that utilizes LLMs as the predictor.<n>Extensive experiments demonstrate that when incorporated into state-of-the-art graph instruction tuning methods, SIT-Graph significantly enhances their performance on text-attributed graph benchmarks.
  arXiv  Detail & Related papers  (2026-01-19T08:10:53Z)
• GILT: An LLM-Free, Tuning-Free Graph Foundational Model for In-Context Learning [50.40400074353263]
  Graph Neural Networks (GNNs) are powerful tools for precessing relational data but often struggle to generalize to unseen graphs.<n>We introduce textbfGraph textbfIn-context textbfL textbfTransformer (GILT), a framework built on an LLM-free and tuning-free architecture.
  arXiv  Detail & Related papers  (2025-10-06T08:09:15Z)
• GraphSOS: Graph Sampling and Order Selection to Help LLMs Understand Graphs Better [13.742220809751627]
  GraphSOS is a novel framework for converting graph data into natural language text.<n>It features an Order Selector Module to ensure proper serialization order of the graph and a Subgraph Sampling Module to sample subgraphs with better structure for better reasoning.<n> Experiments on multiple datasets for node classification and graph question-answering demonstrate that GraphSOS improves LLMs' performance and ability on graph tasks.
  arXiv  Detail & Related papers  (2025-01-24T11:55:57Z)
• What Do LLMs Need to Understand Graphs: A Survey of Parametric Representation of Graphs [69.48708136448694]
  Large language models (LLMs) are reorganizing in the AI community for their expected reasoning and inference abilities.<n>We believe this kind of parametric representation of graphs, graph laws, can be a solution for making LLMs understand graph data as the input.
  arXiv  Detail & Related papers  (2024-10-16T00:01:31Z)
• Can Large Language Models Analyze Graphs like Professionals? A Benchmark, Datasets and Models [88.4320775961431]
  We introduce ProGraph, a benchmark for large language models (LLMs) to process graphs.<n>Our findings reveal that the performance of current LLMs is unsatisfactory, with the best model achieving only 36% accuracy.<n>We propose LLM4Graph datasets, which include crawled documents and auto-generated codes based on 6 widely used graph libraries.
  arXiv  Detail & Related papers  (2024-09-29T11:38:45Z)
• Investigating Instruction Tuning Large Language Models on Graphs [37.20541711360419]
  There's growing interest in applying Large Language Models (LLMs) to graph-related tasks. This study delves into the capabilities of instruction-following LLMs for engaging with real-world graphs.
  arXiv  Detail & Related papers  (2024-08-10T06:54:35Z)
• Graph Chain-of-Thought: Augmenting Large Language Models by Reasoning on Graphs [60.71360240206726]
  Large language models (LLMs) suffer from hallucinations, especially on knowledge-intensive tasks. Existing works propose to augment LLMs with individual text units retrieved from external knowledge corpora. We propose a framework called Graph Chain-of-thought (Graph-CoT) to augment LLMs with graphs by encouraging LLMs to reason on the graph iteratively.
  arXiv  Detail & Related papers  (2024-04-10T15:41:53Z)
• Large Language Models on Graphs: A Comprehensive Survey [77.16803297418201]
  We provide a systematic review of scenarios and techniques related to large language models on graphs. We first summarize potential scenarios of adopting LLMs on graphs into three categories, namely pure graphs, text-attributed graphs, and text-paired graphs. We discuss the real-world applications of such methods and summarize open-source codes and benchmark datasets.
  arXiv  Detail & Related papers  (2023-12-05T14:14:27Z)
• deGraphCS: Embedding Variable-based Flow Graph for Neural Code Search [15.19181807445119]
  We propose a learnable deep Graph for Code Search (called deGraphCS) to transfer source code into variable-based flow graphs. We collect a large-scale dataset from GitHub containing 41,152 code snippets written in C language.
  arXiv  Detail & Related papers  (2021-03-24T06:57:44Z)
• Universal Representation for Code [8.978516631649276]
  We present effective pre-training strategies on top of a novel graph-based code representation. We pre-train graph neural networks on the representation to extract universal code properties. We evaluate our model on two real-world datasets -- spanning over 30M Java methods and 770K Python methods.
  arXiv  Detail & Related papers  (2021-03-04T15:39:25Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.