13 papers
Benchmarking and Enhancing Text-to-Image Models for Generating Visual Representations in Early Arithmetic Education
Junling Wang, Boqi Chen, Heejin Do +3
AI systems are increasingly used to support educational content creation, yet it remains unclear whether they can generate outputs that faithfully represent the pedagogical concept…
Projectional Decoding: Towards Semantic-Aware LLM Generation
Boqi Chen, José Antonio Hernández López, Aren A. Babikian
Large language models (LLMs) are increasingly used to generate software artifacts across many software engineering (SE) tasks, yet ensuring the semantic validity of these artifacts…
LLM-Assisted Repository-Level Generation with Structured Spec-Driven Engineering
Shuzhao Feng, Boqi Chen, Brett H Meyer +1
State-of-the-art Large Language Models (LLMs) excel in code generation at the function level. However, the output quality significantly declines when scaling to repository-level sy…
Structure- and Event-Driven Frameworks for State Machine Modeling with Large Language Models
Samer Abdulkarim, Evan Boyd, Karl Bridi +3
UML state machine design is a critical process in software engineering. Traditionally, state machines are manually crafted by experienced engineers based on natural language requir…
Hierarchical Evaluation of Software Design Capabilities of Large Language Models of Code
Mootez Saad, Boqi Chen, José Antonio Hernández López +2
Large language models (LLMs) are being increasingly adopted in the software engineering domain, yet the robustness of their grasp on core software design concepts remains unclear.…
Certifying Robustness of Graph Convolutional Networks for Node Perturbation with Polyhedra Abstract Interpretation
Boqi Chen, Kristóf Marussy, Oszkár Semeráth +2
Graph convolutional neural networks (GCNs) are powerful tools for learning graph-based knowledge representations from training data. However, they are vulnerable to small perturbat…