Defines documentation-to-code equivalence and introduces Documentary to generate matching docs for 53.4% of function snippets, raising LLM output prediction accuracy by 12.8-24.5% over human-written docs.
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics , pages=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.SE 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
CAIS indexes code, APIs and docs for combined keyword-semantic queries by LLM agents, yielding additional findings and 22-34% time savings in two case studies on a production SDK versus baseline repository tools.
citing papers explorer
-
Natural Language-Focused Software Engineering via Code-Documentation Equivalence
Defines documentation-to-code equivalence and introduces Documentary to generate matching docs for 53.4% of function snippets, raising LLM output prediction accuracy by 12.8-24.5% over human-written docs.
-
Context-as-AI-Service: Surfacing Cross-File Dependency Chains for LLM-Generated Developer Documentation
CAIS indexes code, APIs and docs for combined keyword-semantic queries by LLM agents, yielding additional findings and 22-34% time savings in two case studies on a production SDK versus baseline repository tools.