From the 2 of 9 linked papers with an AI index.
9 papers
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
The paper introduces a curated multilingual benchmark to study how the natural language of prompts influences code generation quality of large language models, evaluating functiona…
Quantize with Confidence? An Empirical Study of Quantization for Code Generation
Saima Afrin, Md. Zahidul Haque, Antonio Mastropaolo
The paper empirically evaluates six post‑training quantization methods for large code generation models, measuring their effects on functional correctness, code quality, and robust…
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…
Understanding and Reducing Metadata-Driven Host Overheads in Sampling-Based GNN Training
Yidong Gong, Saima Afrin, Yuchen Ma +3
Modern deep learning workloads increasingly exhibit dynamic, metadata-driven execution, where runtime-generated information determines memory provisioning and kernel launch decisio…
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…
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…