CIAO uses LLMs to generate standards-based system-level software architecture documentation from code repositories, with a developer study showing it is generally valuable, comprehensible, and accurate.
Available: https://proceedings.neurips.cc/paper files/ paper/2020/file/1457c0d6bfcb4967418bfb8ac142f64a-Paper.pdf
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
years
2026 3verdicts
UNVERDICTED 3roles
background 2representative citing papers
Tag-based few-shot selection yields higher precision and stability than random or similarity-based methods when using LLMs to analyze medical incidents.
Vision-language models can serve as zero-shot ODD sensors for autonomous driving when using definition-anchored chain-of-thought prompting with persona decomposition.
citing papers explorer
-
CIAO - Code In Architecture Out - Automated Software Architecture Documentation with Large Language Models
CIAO uses LLMs to generate standards-based system-level software architecture documentation from code repositories, with a developer study showing it is generally valuable, comprehensible, and accurate.
-
Medical Incident Causal Factors and Preventive Measures Generation Using Tag-based Example Selection in Few-shot Learning
Tag-based few-shot selection yields higher precision and stability than random or similarity-based methods when using LLMs to analyze medical incidents.
-
Operating Within the Operational Design Domain: Zero-Shot Perception with Vision-Language Models
Vision-language models can serve as zero-shot ODD sensors for autonomous driving when using definition-anchored chain-of-thought prompting with persona decomposition.