StackRepoQA shows LLMs reach only moderate accuracy on multi-file Java QA tasks, with gains from graph-based retrieval but frequent reliance on verbatim answer reproduction.
Vaillant, Felipe Deveza de Almeida, Paulo Anselmo M
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
Longitudinal surveys show AI coding assistants reduce time on code writing but increase supervisory verification tasks, with stable productivity perceptions yet rising reports of worsened developer experience.
citing papers explorer
-
Beyond Code Snippets: Benchmarking LLMs on Repository-Level Question Answering
StackRepoQA shows LLMs reach only moderate accuracy on multi-file Java QA tasks, with gains from graph-based retrieval but frequent reliance on verbatim answer reproduction.
-
The Impact of AI Coding Assistants on Software Engineering: A Longitudinal Study
Longitudinal surveys show AI coding assistants reduce time on code writing but increase supervisory verification tasks, with stable productivity perceptions yet rising reports of worsened developer experience.