314 citations · 949 across the 61 of their papers we have counts for
65 papers
Can LLMs Test Terminal User Interfaces?
Chao Peng, Ruida Hu, Ajitha Rajan +3
Terminal User Interfaces (TUIs) combine the stateful, screen-oriented behaviour of GUIs with terminal deployment and are now common in developer tools. Yet they lack a dedicated te…
Assessing Spear-Phishing Website Generation in Large Language Model Coding Agents
Tailia Malloy, Tegawende F. Bissyande
Large Language Models are expanding beyond being a tool humans use and into independent agents that can observe an environment, reason about solutions to problems, make changes tha…
Exploring Hidden Geographic Disparities in Android Apps
M. Alecci, P. Jiménez, J. Samhi +2
While mobile app evolution has been widely studied, geographical variation in app behavior remains largely unexplored. This paper presents a large-scale study of location-based And…
SIEVE: Towards Verifiable Certification for Code-datasets
Fatou Ndiaye Mbodji, El-hacen Diallo, Jordan Samhi +3
Code agents and empirical software engineering rely on public code datasets, yet these datasets lack verifiable quality guarantees. Static 'dataset cards' inform, but they are neit…
Do Large Language Models Grasp The Grammar? Evidence from Grammar-Book-Guided Probing in Luxembourgish
Lujun Li, Yewei Song, Lama Sleem +7
Grammar refers to the system of rules that governs the structural organization and the semantic relations among linguistic units such as sentences, phrases, and words within a give…
Reinforcement Learning-Guided Chain-of-Draft for Token-Efficient Code Generation
Xunzhu Tang, Iyiola Emmanuel Olatunji, Tiezhu Sun +2
LLMs demonstrate surface-level fluency in code generation but struggle with structured reasoning tasks requiring correctness and semantic alignment. While Chain-of-Thought (CoT) pr…
Multi-Agent Strategies for Bridging Programming Language Gaps in Code Generation
Micheline Bénédicte Moumoula, Serge Lionel Nikiema, Albérick Euraste Djire +3
Real-world software systems are inherently multilingual, but current large language models are not equally consistent across programming languages. This mismatch limits code genera…
Security Evaluation of Android apps in budget African Mobile Devices
Alioune Diallo, Anta Diop, Abdoul Kader Kabore +4
Android's open-source nature facilitates widespread smartphone accessibility, particularly in price-sensitive markets. System and vendor applications that come pre-installed on bud…
Detection of security smells in IaC scripts through semantics-aware code and language processing
Aicha War, Adnan A. Rawass, Abdoul K. Kabore +3
Infrastructure as Code (IaC) automates the provisioning and management of IT infrastructure through scripts and tools, streamlining software deployment. Prior studies have shown th…
Security smells in infrastructure as code: a taxonomy update beyond the seven sins
Aicha War, Serge L. B. Nikiema, Jordan Samhi +2
Infrastructure as Code (IaC) has become essential for modern software management, yet security flaws in IaC scripts can have severe consequences, as exemplified by the recurring ex…
How Small Transformation Expose the Weakness of Semantic Similarity Measures
Serge Lionel Nikiema, Albérick Euraste Djire, Abdoul Aziz Bonkoungou +5
This research examines how well different methods measure semantic similarity, which is important for various software engineering applications such as code search, API recommendat…
Measuring LLM Code Generation Stability via Structural Entropy
Yewei Song, Tiezhu Sun, Xunzhu Tang +3
Assessing the stability of code generation from large language models (LLMs) is essential for judging their reliability in real-world development. We extend prior "structural-entro…
Toward an African Agenda for AI Safety
Samuel T. Segun, Rachel Adams, Ana Florido +22
This paper maps Africa's distinctive AI risk profile, from deepfake fuelled electoral interference and data colonial dependency to compute scarcity, labour disruption and dispropor…
A Survey of LLM-based Automated Program Repair: Taxonomies, Design Paradigms, and Applications
Boyang Yang, Zijian Cai, Fengling Liu +5
Large language models (LLMs) are reshaping automated program repair. We present a reproducible hierarchical taxonomy that organizes 66 LLM-based repair systems according to where r…
Unlocking LLM Repair Capabilities Through Cross-Language Translation and Multi-Agent Refinement
Wenqiang Luo, Jacky Wai Keung, Boyang Yang +4
Recent advances in leveraging LLMs for APR have demonstrated impressive capabilities in fixing software defects. However, current LLM-based approaches predominantly focus on mainst…
Programming Language Confusion: When Code LLMs Can't Keep their Languages Straight
Micheline Bénédicte Moumoula, Serge Lionel Nikiema, Abdoul Kader Kabore +2
Large Language Models (LLMs) have achieved state-of-the-art performance across software engineering tasks, from code generation to translation. However, we identify and systematica…
When Fine-Tuning LLMs Meets Data Privacy: An Empirical Study of Federated Learning in LLM-Based Program Repair
Wenqiang Luo, Jacky Wai Keung, Boyang Yang +5
Software systems have been evolving rapidly and inevitably introducing bugs at an increasing rate, leading to significant losses in resources consumed by software maintenance. Rece…
ContractTrace: Retracing Smart Contract Versions for Security Analyses
Fatou Ndiaye Mbodji, Vinny Adjibi, Moustapha Awwalou Diouf +4
Due to the inherent immutability of blockchain technology, smart contract updates require their deployment at new addresses rather than modifying existing ones, thus fragmenting ve…
Security Assessment of Mobile Banking Apps in West African Economic and Monetary Union
Alioune Diallo, Aicha War, Moustapha Awwalou Diouf +4
The West African Economic and Monetary Union (WAEMU) states, characterized by widespread smartphone usage, have witnessed banks and financial institutions introducing mobile bankin…
In-Context Code-Text Learning for Bimodal Software Engineering
Xunzhu Tang, Liran Wang, Yonghui Liu +6
Bimodal software analysis initially appeared to be within reach with the advent of large language models. Unfortunately, the complex interplay of natural language text and code in…
On the Diffusion of Test Smells in LLM-Generated Unit Tests
Wendkûuni C. Ouédraogo, Yinghua Li, Xueqi Dang +5
LLMs promise to transform unit test generation from a manual burden into an automated solution. Yet, beyond metrics such as compilability or coverage, little is known about the qua…
The Struggles of LLMs in Cross-lingual Code Clone Detection
Micheline Bénédicte Moumoula, Abdoul Kader Kabore, Jacques Klein +1
With the involvement of multiple programming languages in modern software development, cross-lingual code clone detection has gained traction within the software engineering commun…
Call Graph Soundness in Android Static Analysis
Jordan Samhi, René Just, Tegawendé F. Bissyandé +2
Static analysis is sound in theory, but an implementation may unsoundly fail to analyze all of a program's code. Any such omission is a serious threat to the validity of the tool's…
LLM for Mobile: An Initial Roadmap
Daihang Chen, Yonghui Liu, Mingyi Zhou +7
When mobile meets LLMs, mobile app users deserve to have more intelligent usage experiences. For this to happen, we argue that there is a strong need to appl LLMs for the mobile ec…