MultiLogBench shows that LLM performance on automated logging varies substantially across programming languages, demonstrating that single-language evidence is insufficient for general claims about model behavior or tool design.
Unilog: Automatic logging via LLM and in-context learning
9 Pith papers cite this work. Polarity classification is still indexing.
9
Pith papers citing it
citation-role summary
baseline 2
background 1
citation-polarity summary
representative citing papers
A large-scale study of real-world repositories finds that AI-generated code differs from human-written code in complexity, structural traits, defect indicators, and commit-level activity patterns.
IntentTester migrates tests across libraries using TDL abstraction and multi-agent LLM synthesis, achieving 85% correctness and 74% effectiveness versus 51% and 43% for baselines on nine projects in JSON, HTML, and Time domains.
A systematic review of on-device AI inference security finds defenses are imbalanced, with roughly half focused on IP theft while one-third of attacks (adversarial examples) lack any associated defenses.
Empirical analysis of 4707 MoltBook posts shows AI-only technical discourse focuses on security, trust, and abstract topics while lacking concrete runtime and project details found in human GitHub discussions.
A survey of 419 practitioners shows strong reliance on reusable GitHub Actions for core CI/CD tasks but limited adoption of reusable workflows, with copy-pasting remaining common due to versioning and trust issues.
AdaDec improves Pass@1 accuracy of LLM code generation by up to 20.9% over greedy decoding by triggering lookahead reranking only at high-uncertainty steps on HumanEval+, MBPP+, and DevEval.
LogCopilot is an LLM framework that builds a hierarchical knowledge base from logs and generates/executes LogQL queries from natural language instructions, reporting 76.8% average accuracy across four datasets.
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
-
AdaDec: A Uncertainty-Guided Lookahead Decoding Framework for LLM-Based Code Generation
AdaDec improves Pass@1 accuracy of LLM code generation by up to 20.9% over greedy decoding by triggering lookahead reranking only at high-uncertainty steps on HumanEval+, MBPP+, and DevEval.