conf.researchr.org / Daniel Rodriguez-Cardenas
Registered user since Tue 4 Jul 2023
Name:Daniel Rodriguez-Cardenas
Country:United States
Affiliation:William & Mary
X (Twitter): https://x.com/danielrc
Research interests:Machine Learning, Interpretability, LLM for SE benchmarking
Contributions
2026
FORGE
- Author of Tricky²: Towards a Benchmark for Evaluating Human and LLM Error Interactions within the Data and Benchmarking-track
- Author of Detecting and Correcting Hallucinations in LLM-Generated Code via Deterministic AST Analysis within the Research Papers-track
- Session Chair of Session III - Code Generation & Migration (part of Research Papers)
- Author of Towards Comprehensive Benchmarking Infrastructure for LLMs In Software Engineering within the Data and Benchmarking-track