Participatory design study with 17 practitioners yields a three-level trust-calibrated review workflow for LLM-generated multi-file code changes, validated positively by 43 practitioners in survey.
Exploring variable potential for llm-based log parsing efficiency and reduced costs
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
fields
cs.SE 3years
2026 3verdicts
UNVERDICTED 3roles
background 1polarities
background 1representative citing papers
Eye-tracking experiment finds that labeling code as LLM-generated increases fixation time without changing review thoroughness, with reviewers adapting criteria or using the prompt.
Systematic review of 145 papers on LLM-based log analysis, providing a unified taxonomy, common design patterns, evaluation practices, and challenges for deployment under drift and limited labels.
citing papers explorer
-
LLM4Log: A Systematic Review of Large Language Model-based Log Analysis
Systematic review of 145 papers on LLM-based log analysis, providing a unified taxonomy, common design patterns, evaluation practices, and challenges for deployment under drift and limited labels.