Related papers: The Code Barrier: What LLMs Actually Understand?

Code reasoning is a fundamental capability for large language models (LLMs) in the code domain. It involves understanding and predicting a program's execution behavior, such as determining the output for a given input or whether a specific…

Large Language Models (LLMs) have demonstrated impressive capabilities in understanding and generating codes. Due to these capabilities, many recent methods are proposed to automatically refine the codes with LLMs. However, we should…

Automating the decision of whether a code change requires manual review is vital for maintaining software quality in modern development workflows. However, the emergence of new programming languages and frameworks creates a critical…

We present two comprehensive benchmarks to evaluate the performance of language models in coding assistance tasks, covering code writing, debugging, code review, and conceptual understanding. Our main contribution includes two curated…

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,…

JavaScript's widespread adoption has made it an attractive target for malicious attackers who employ sophisticated obfuscation techniques to conceal harmful code. Current deobfuscation tools suffer from critical limitations that severely…

Security vulnerabilities present in a code that has been written in diverse programming languages are among the most critical yet complicated aspects of source code to detect. Static analysis tools based on rule-based patterns usually do…

With the recent advancement of Large Language Models (LLMs), generating functionally correct code has become less complicated for a wide array of developers. While using LLMs has sped up the functional development process, it poses a heavy…

We present an empirical evaluation of Large Language Models in code understanding associated with non-trivial, semantic-preserving program transformations such as copy propagation or constant folding. Our findings show that LLMs fail to…

Leveraging Large Language Models (LLMs) for code generation has increasingly emerged as a common practice in the domain of software engineering. Relevant benchmarks have been established to evaluate the code generation capabilities of LLMs.…

The rise of large language models (LLMs) has significantly impacted various domains, including natural language processing (NLP) and image generation, by making complex computational tasks more accessible. While LLMs demonstrate impressive…

The increasing development of LLMs in code generation has drawn significant attention among researchers. To enhance LLM-based code generation ability, current efforts are predominantly directed towards collecting high-quality datasets and…

Deep learning-based approaches, particularly those leveraging pre-trained language models (PLMs), have shown promise in automated software vulnerability detection. However, existing methods are predominantly limited to specific programming…

Past research has examined how well these models grasp code syntax, yet their understanding of code semantics still needs to be explored. We extensively analyze seven code models to investigate how code models represent code syntax and…

In large language models (LLMs), code and reasoning reinforce each other: code offers an abstract, modular, and logic-driven structure that supports reasoning, while reasoning translates high-level goals into smaller, executable steps that…

The advent of large language models (LLMs) has significantly advanced artificial intelligence (AI) in software engineering (SE), with source code embeddings playing a crucial role in tasks such as source code clone detection and source code…

Automating code documentation through explanatory text can prove highly beneficial in code understanding. Large Language Models (LLMs) have made remarkable strides in Natural Language Processing, especially within software engineering tasks…

Large language models (LLMs) has experienced exponential growth, they demonstrate remarkable performance across various tasks. Notwithstanding, contemporary research primarily centers on enhancing the size and quality of pretraining data,…

Context: Traditional software security analysis methods struggle to keep pace with the scale and complexity of modern codebases, requiring intelligent automation to detect, assess, and remediate vulnerabilities more efficiently and…

Qualitative data analysis provides insight into the underlying perceptions and experiences within unstructured data. However, the time-consuming nature of the coding process, especially for larger datasets, calls for innovative approaches,…