arXiv:2503.07329v2 Announce Type: replace-cross
Abstract: The impact of random seeds in fine-tuning large language models (LLMs) has been largely overlooked despite its potential influence on model performance.In this study, we systematically evaluate the effects of random seeds on LLMs using the GLUE and SuperGLUE benchmarks. We analyze the macro-level impact through traditional metrics like accuracy and F1, calculating their mean and variance to quantify performance fluctuations. To capture the micro-level effects, we introduce a novel metric, consistency, measuring the stability of individual predictions across runs. Our experiments reveal significant variance at both macro and micro levels, underscoring the need for careful consideration of random seeds in fine-tuning and evaluation.
Uncovering Code Insights: Leveraging GitHub Artifacts for Deeper Code Understanding
arXiv:2511.03549v1 Announce Type: cross Abstract: Understanding the purpose of source code is a critical task in software maintenance, onboarding, and modernization. While large language models