DCE-LLM: Dead Code Elimination with Large Language Models

2025/06/04 by Minyu Chen, Guoqiang Li, Chen, Minyu +5
Computer Science · #FOS: Computer and information sciences #Natural Language Processing Techniques #Software Engineering (cs.SE) #Text Readability and Simplification #Web Application Security Vulnerabilities

paper · pdf · doi:10.48550/arxiv.2506.11076

openalex publication_date 2025/06/04 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Dead code introduces several challenges in software development, such as increased binary size and maintenance difficulties. It can also obscure logical errors and be exploited for obfuscation in malware. For LLM-based code-related tasks, dead code introduces vulnerabilities that can mislead these models, raising security concerns. Although modern compilers and IDEs offer dead code elimination, sophisticated patterns can bypass these tools. A universal approach that includes classification, location, explanation, and correction is needed, yet current tools often require significant manual effort. We present DCE-LLM, a framework for automated dead code elimination using a small CodeBERT model with an attribution-based line selector to efficiently locate suspect code. LLMs then generate judgments and explanations, fine-tuned on a large-scale, annotated dead code dataset to provide detailed explanations and patches. DCE-LLM outperforms existing tools, with advanced unreachability detection, automated correction, and support for multiple programming languages. Experimental results show DCE-LLM achieves over 94% F1 scores for unused and unreachable code, significantly surpassing GPT-4o by 30%.

Citations

• Code Repair with LLMs gives an Exploration-Exploitation Tradeoff
• LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models
• Rewriting the Code: A Simple Method for Large Language Model Augmented Code Search
• LLM-Assisted Code Cleaning For Training Accurate Code Generators
• Understanding the Effectiveness of Large Language Models in Detecting Security Vulnerabilities
• Large Language Models for Test-Free Fault Localization
• Efficient Memory Management for Large Language Model Serving with PagedAttention
• The effectiveness of feature attribution methods and its correlation\n with automatic evaluation scores
• CodeNet: A Large-Scale AI for Code Dataset for Learning a Diversity of Coding Tasks
• Interpretation of NLP models through input marginalization
• CodeBERT: A Pre-Trained Model for Programming and Natural Languages
• CodeBERT: A Pre-Trained Model for Programming and Natural Languages
• Understanding Neural Networks through Representation Erasure

Cited by

• FCGHunter: Towards Evaluating Robustness of Graph-Based Android Malware Detection

Related

• Beyond Natural Language Perplexity: Detecting Dead Code Poisoning in Code Generation Datasets
• The CodeInverter Suite: Control-Flow and Data-Mapping Augmented Binary Decompilation with LLMs
• From Vulnerabilities to Remediation: A Systematic Literature Review of LLMs in Code Security
• LLM4CVE: Enabling Iterative Automated Vulnerability Repair with Large Language Models
• Synthetic Code Surgery: Repairing Bugs and Vulnerabilities with LLMs and Synthetic Data