# Enhancing Semantic Understanding in Pointer Analysis using Large Language Models

## TL;DR

This paper introduces LMPA, a novel pointer analysis framework that leverages large language models to improve semantic understanding, accuracy, and scalability by better modeling user-defined functions and summaries.

## Contribution

The paper proposes LMPA, integrating LLMs into pointer analysis to address semantic limitations and improve precision and scalability in static code analysis.

## Key findings

- LMPA effectively models user-defined functions resembling system APIs.
- Enhanced summary strategies improve points-to set inference.
- LMPA mitigates incorrect propagation of facts in pointer analysis.

## Abstract

Pointer analysis has been studied for over four decades. However, existing frameworks continue to suffer from the propagation of incorrect facts. A major limitation stems from their insufficient semantic understanding of code, resulting in overly conservative treatment of user-defined functions. Recent advances in large language models (LLMs) present new opportunities to bridge this gap. In this paper, we propose LMPA (LLM-enhanced Pointer Analysis), a vision that integrates LLMs into pointer analysis to enhance both precision and scalability. LMPA identifies user-defined functions that resemble system APIs and models them accordingly, thereby mitigating erroneous cross-calling-context propagation. Furthermore, it enhances summary-based analysis by inferring initial points-to sets and introducing a novel summary strategy augmented with natural language. Finally, we discuss the key challenges involved in realizing this vision.