98 citations · 122 across the 38 of their papers we have counts for
41 papers
Pattern over Pixels: Measuring Pattern Completion Bias in Multimodal Code Generation
Khai-Nguyen Nguyen, Oscar Chaparro, Antonio Mastropaolo
Multimodal large language models (MLLMs) are increasingly used to translate webpage screenshots into front-end code, but repeated UI patterns may sway them toward visually incorrec…
Large Language Models for Code Generation from Multilingual Prompts: A Curated Benchmark and a Study on Code Quality
Saima Afrin, Alessandro Midolo, Camilo Escobar-Velásquez +5
Large Language Models (LLMs) perform differently on identical programming tasks when prompted in different natural languages, a phenomenon known as language bias. While this behavi…
Quantize with Confidence? An Empirical Study of Quantization for Code Generation
Saima Afrin, Md. Zahidul Haque, Antonio Mastropaolo
The growing adoption of local inference frameworks such as Ollama has made it increasingly common for developers to run large code models on laptops and other resource-constrained…
Prior Bias in Vision Language Models on UML Diagram Interpretation
Zaiyu Cheng, Khai-Nguyen Nguyen, Antonio Mastropaolo
Vision Language Models (VLMs) are increasingly applied to software engineering artifacts, especially UML class diagrams whose meaning depends on visual notation. Yet, it is unclear…
Rethinking Software Empirical Studies with Structural Causal Models
Daniel Rodriguez-Cardenas, Aya Garryyeva, David Nader Palacio +2
Causal Inference offers a fundamental approach for advancing empirical software engineering (ESE) beyond traditional statistical association, enabling researchers to rigorously ide…
Prompt-Driven Code Summarization: A Systematic Literature Review
Afia Farjana, Zaiyu Cheng, Antonio Mastropaolo
Software documentation is essential for program comprehension, developer onboarding, code review, and long-term maintenance. Yet producing quality documentation manually is time-co…
Recovering Fine-Grained Code Change Rationale from Multiple Software Artifacts
Mehedi Sun, Antu Saha, Nadeeshan De Silva +2
Understanding the reasons behind past code changes is critical for refactoring, code review, and debugging. However, code change rationale is often fragmented, inconsistently docum…
Developers and Generative AI: A Study of Self-Admitted Usage in Open Source Projects
Rosalia Tufano, Federica Pepe, Fiorella Zampetti +4
The availability of generative Artificial Intelligence (AI) tools such as ChatGPT or GitHub Copilot is reshaping the way in which software is developed, evolved, and maintained. Of…
An Empirical Study on the Effects of System Prompts in Instruction-Tuned Models for Code Generation
Zaiyu Cheng, Antonio Mastropaolo
Instruction-tuned Language Models (ILMs) have become essential components of modern AI systems, demonstrating exceptional versatility across natural language and reasoning tasks. A…
Towards Comprehensive Benchmarking Infrastructure for LLMs In Software Engineering
Daniel Rodriguez-Cardenas, Xiaochang Li, Marcos Macedo +5
Large language models for code are advancing fast, yet our ability to evaluate them lags behind. Current benchmarks focus on narrow tasks and single metrics, which hide critical ga…
Not All Tokens Matter: Data-Centric Optimization for Efficient Code Summarization
Saima Afrin, Zaiyu Cheng, Tushar Sharma +3
The rapid advancement of Large Language Models (LLMs) has revolutionized software engineering automation, particularly in automated code summarization, which enhances program compr…
Parameter-Efficient Multi-Task Fine-Tuning in Code-Related Tasks
Md Zahidul Haque, Saima Afrin, Antonio Mastropaolo
Large Language Models (LLMs) have proven highly effective in automating software engineering tasks, bridging natural language and code semantics to achieve notable results in code…
Toward Explaining Large Language Models in Software Engineering Tasks
Antonio Vitale, Khai-Nguyen Nguyen, Denys Poshyvanyk +3
Recent progress in Large Language Models (LLMs) has substantially advanced the automation of software engineering (SE) tasks, enabling complex activities such as code generation an…
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…
Is Quantization a Deal-breaker? Empirical Insights from Large Code Models
Saima Afrin, Bowen Xu, Antonio Mastropaolo
The growing scale of large language models (LLMs) not only demands extensive computational resources but also raises environmental concerns due to their increasing carbon footprint…
Smaller = Weaker? Benchmarking Robustness of Quantized LLMs in Code Generation
Sen Fang, Weiyuan Ding, Antonio Mastropaolo +1
Quantization has emerged as a mainstream method for compressing Large Language Models (LLMs), reducing memory requirements and accelerating inference without architectural modifica…
A Path Less Traveled: Reimagining Software Engineering Automation via a Neurosymbolic Paradigm
Antonio Mastropaolo, Denys Poshyvanyk
The emergence of Large Code Models (LCMs) has transformed software engineering (SE) automation, driving significant advancements in tasks such as code generation, source code docum…
A Systematic Literature Review of Parameter-Efficient Fine-Tuning for Large Code Models
Saima Afrin, Md Zahidul Haque, Antonio Mastropaolo
The rise of Artificial Intelligence (AI)-and particularly Large Language Models (LLMs) for code-has reshaped Software Engineering (SE) by enabling the automation of tasks such as c…
Evaluating the Impact of Post-Training Quantization on Large Language Models for Code Generation
Alessandro Giagnorio, Antonio Mastropaolo, Saima Afrin +2
Large Language Models (LLMs) have shown an impressive capability in code generation. The LLM effectiveness generally increases with its size: The higher the number of LLM's trainab…
Optimizing Datasets for Code Summarization: Is Code-Comment Coherence Enough?
Antonio Vitale, Antonio Mastropaolo, Rocco Oliveto +2
Automated code summarization is a long-standing goal for code comprehension. This task automatically generates documentation using a given method. Deep Learning (DL)-based approach…
Resource-Efficient & Effective Code Summarization
Saima Afrin, Joseph Call, Khai-Nguyen Nguyen +2
Code Language Models (CLMs) have demonstrated high effectiveness in automating software engineering tasks such as bug fixing, code generation, and code documentation. This progress…
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…
A Taxonomy of Self-Admitted Technical Debt in Deep Learning Systems
Federica Pepe, Fiorella Zampetti, Antonio Mastropaolo +2
The development of Machine Learning (ML)- and, more recently, of Deep Learning (DL)-intensive systems requires suitable choices, e.g., in terms of technology, algorithms, and hyper…
The Rise and Fall(?) of Software Engineering
Antonio Mastropaolo, Camilo Escobar-Velásquez, Mario Linares-Vásquez
Over the last ten years, the realm of Artificial Intelligence (AI) has experienced an explosion of revolutionary breakthroughs, transforming what seemed like a far-off dream into a…