4 citations · 14 across the 15 of their papers we have counts for
15 papers
CauSec: Unboxing the Causal Drivers of Static Vulnerability Analysis Performance
Akram Khan, Md Akram Khan, Daniel Rodriguez-Cardenas +3
Static Application Security Testing (SAST) tools are widely used in both industry and academia. Such tools often make design choices that sacrifice detection to achieve higher perf…
ECLAIR: A Causally-Grounded AI Framework for Scientific Discovery in Empirical Software Engineering
Alejandro Velasco, Daniel Rodriguez-Cardenas, Dipin Khati +2
The scientific method has long guided empirical research in Software Engineering (SE), but the complexity of modern software systems often hinders its systematic application. This…
On Automated and Explainable Provenance of AI-Generated Code
Alejandro Velasco, Nathan Wintersgill, Trevor Stalnaker +2
Generative AI for code generation has transformed software development, but it has also introduced a critical transparency problem: the origins of AI-generated code are opaque to t…
How Do Semantically Equivalent Code Transformations Impact Membership Inference on LLMs for Code?
Hua Yang, Alejandro Velasco, Thanh Le-Cong +3
The success of large language models for code relies on vast amounts of code data, including public open-source repositories, such as GitHub, and private, confidential code from co…
Understanding Privacy Risks in Code Models Through Training Dynamics: A Causal Approach
Hua Yang, Alejandro Velasco, Sen Fang +2
Large language models for code (LLM4Code) have greatly improved developer productivity but also raise privacy concerns due to their reliance on open-source repositories containing…
A Causal Perspective on Measuring, Explaining and Mitigating Smells in LLM-Generated Code
Alejandro Velasco, Daniel Rodriguez-Cardenas, Dipin Khati +3
Recent advances in large language models (LLMs) have accelerated their adoption in software engineering contexts. However, concerns persist about the structural quality of the code…
On the Effectiveness of LLM-as-a-judge for Code Generation and Summarization
Giuseppe Crupi, Rosalia Tufano, Alejandro Velasco +3
Large Language Models have been recently exploited as judges for complex natural language processing tasks, such as Q&A. The basic idea is to delegate to an LLM the assessment of t…
Enabling Global, Human-Centered Explanations for LLMs:From Tokens to Interpretable Code and Test Generation
Dipin Khati, Daniel Rodriguez-Cardenas, David N. Palacio +3
As Large Language Models for Code (LM4Code) become integral to software engineering, establishing trust in their output becomes critical. However, standard accuracy metrics obscure…
Mapping the Trust Terrain: LLMs in Software Engineering -- Insights and Perspectives
Dipin Khati, Yijin Liu, David N. Palacio +2
Applications of Large Language Models (LLMs) are rapidly growing in industry and academia for various software engineering (SE) tasks. As these models become more integral to criti…
SnipGen: A Mining Repository Framework for Evaluating LLMs for Code
Daniel Rodriguez-Cardenas, Alejandro Velasco, Denys Poshyvanyk
Language Models (LLMs), such as transformer-based neural networks trained on billions of parameters, have become increasingly prevalent in software engineering (SE). These models,…
Toward Neurosymbolic Program Comprehension
Alejandro Velasco, Aya Garryyeva, David N. Palacio +2
Recent advancements in Large Language Models (LLMs) have paved the way for Large Code Models (LCMs), enabling automation in complex software engineering tasks, such as code generat…
How Propense Are Large Language Models at Producing Code Smells? A Benchmarking Study
Alejandro Velasco, Daniel Rodriguez-Cardenas, Luftar Rahman Alif +2
Large Language Models (LLMs) have shown significant potential in automating software engineering tasks, particularly in code generation. However, current evaluation benchmarks, whi…
Measuring Emergent Capabilities of LLMs for Software Engineering: How Far Are We?
Conor O'Brien, Daniel Rodriguez-Cardenas, Alejandro Velasco +2
The adoption of Large Language Models (LLMs) across multiple contexts has sparked interest in understanding how scaling model size might lead to behavioral changes, as LLMs can exh…
Towards More Trustworthy and Interpretable LLMs for Code through Syntax-Grounded Explanations
David N. Palacio, Daniel Rodriguez-Cardenas, Alejandro Velasco +3
Trustworthiness and interpretability are inextricably linked concepts for LLMs. The more interpretable an LLM is, the more trustworthy it becomes. However, current techniques for i…
Which Syntactic Capabilities Are Statistically Learned by Masked Language Models for Code?
Alejandro Velasco, David N. Palacio, Daniel Rodriguez-Cardenas +1
This paper discusses the limitations of evaluating Masked Language Models (MLMs) in code completion tasks. We highlight that relying on accuracy-based measurements may lead to an o…