LLMs improve log level prediction using socio-technical context

Researchers have developed a new retrieval-based approach for Large Language Models (LLMs) to predict log levels in software development, aiming to improve efficiency and accuracy. This method leverages socio-technical context, considering both code functionality and developer ownership, rather than relying on random examples. The proposed technique significantly outperforms random baselines and existing supervised predictors, achieving higher AUC scores across multiple Java projects. AI

IMPACT Enhances LLM utility in software engineering by improving log analysis accuracy and efficiency.

RANK_REASON The cluster contains an academic paper detailing a new method for log level prediction using LLMs. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.LG →

• DeepLV: Suggesting Log Levels Using Ordinal Based Neural Networks
• Few-shot learning
• Java
• large-language models
• Youssef Esseddiq Ouatiti

• paper
• product

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →