A review of 114 studies creates taxonomies for code and data quality issues, formalizes 18 propagation mechanisms from training data defects to LLM-generated code defects, and synthesizes detection and mitigation techniques.
Lost at C: A user study on the security implications of large language model code assistants,
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
StarCoderBase matches or beats OpenAI's code-cushman-001 on multi-language code benchmarks; the Python-fine-tuned StarCoder reaches 40% pass@1 on HumanEval while retaining other-language performance.
Proposes a traceable multilayer security model for spec-driven AI development and reports reduced modal failures (50 to 36) in a 221-test backend generation study when the model conditions the LLM.
citing papers explorer
-
Bridging Generation and Training: A Systematic Review of Quality Issues in LLMs for Code
A review of 114 studies creates taxonomies for code and data quality issues, formalizes 18 propagation mechanisms from training data defects to LLM-generated code defects, and synthesizes detection and mitigation techniques.
-
Specification-Driven Development Benchmark: Security Knowledge Transition
Proposes a traceable multilayer security model for spec-driven AI development and reports reduced modal failures (50 to 36) in a 221-test backend generation study when the model conditions the LLM.