Enhancing Semantic Understanding in Pointer Analysis using Large Language Models

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Cheng, Baijun, Wang, Kailong, Shi, Ling, Wang, Haoyu, Guo, Yao, Li, Ding, Chen, Xiangqun
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866915470202896384
author Cheng, Baijun
Wang, Kailong
Shi, Ling
Wang, Haoyu
Guo, Yao
Li, Ding
Chen, Xiangqun
author_facet Cheng, Baijun
Wang, Kailong
Shi, Ling
Wang, Haoyu
Guo, Yao
Li, Ding
Chen, Xiangqun
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2508_21454
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Enhancing Semantic Understanding in Pointer Analysis using Large Language Models
Cheng, Baijun
Wang, Kailong
Shi, Ling
Wang, Haoyu
Guo, Yao
Li, Ding
Chen, Xiangqun
Software Engineering
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.
title Enhancing Semantic Understanding in Pointer Analysis using Large Language Models
topic Software Engineering
url https://arxiv.org/abs/2508.21454