Pseudocode-Injection Magic: Enabling LLMs to Tackle Graph Computational Tasks

2025-01-23

AI Summary

Large language models (LLMs) struggle with graph-structured data modeling, incur high inference overhead, and generalize poorly to ultra-large-scale graph computation tasks. To address these challenges, this paper proposes PIE—a three-stage framework comprising structured problem understanding, pseudocode-injected prompting, and interpreter-driven code generation—decoupling graph analysis from execution. Its core innovation is the first-ever pseudocode injection mechanism, which guides the LLM to generate reusable, efficient graph algorithm code in a single call; this code is then executed and verified by a lightweight interpreter. Consequently, PIE achieves one-time LLM invocation with zero-shot generalization across multiple graph instances. Experiments demonstrate that PIE outperforms all baselines in both accuracy and efficiency across diverse graph computation tasks, reducing inference cost by 72%.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Natural Language Processing: Code Generation / Program Synthesis from Natural Language
• Planning, Routing, and Scheduling: Planning with Language Models

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems

Abstract

Graph computational tasks are inherently challenging and often demand the development of advanced algorithms for effective solutions. With the emergence of large language models (LLMs), researchers have begun investigating their potential to address these tasks. However, existing approaches are constrained by LLMs' limited capability to comprehend complex graph structures and their high inference costs, rendering them impractical for handling large-scale graphs. Inspired by human approaches to graph problems, we introduce a novel framework, PIE (Pseudocode-Injection-Enhanced LLM Reasoning for Graph Computational Tasks), which consists of three key steps: problem understanding, prompt design, and code generation. In this framework, LLMs are tasked with understanding the problem and extracting relevant information to generate correct code. The responsibility for analyzing the graph structure and executing the code is delegated to the interpreter. We inject task-related pseudocodes into the prompts to further assist the LLMs in generating efficient code. We also employ cost-effective trial-and-error techniques to ensure that the LLM-generated code executes correctly. Unlike other methods that require invoking LLMs for each individual test case, PIE only calls the LLM during the code generation phase, allowing the generated code to be reused and significantly reducing inference costs. Extensive experiments demonstrate that PIE outperforms existing baselines in terms of both accuracy and computational efficiency.

Problem

• Large Language Models
• Complex Graph Computations
• Massive Graph Data

Innovation

• PIE Framework
• Pseudo-code Prompts
• Cost-efficient Trial-and-error