activity
20242026
collaborators

12 papers

cs.SE2026

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…

cs.SE2026

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…

cs.SE2026

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…

cs.SE2026

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…

cs.SE2026

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…

cs.SE2025

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…