LLM code generation lacks syntactic robustness on math-formula prompts, but formula-reduction pre-processing raises it from 54.05% to 74.42%.
An empirical study of the code generation of safety-critical software using llms,
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.SE 2verdicts
UNVERDICTED 2representative citing papers
Survey of 188 engineers using SEM finds that UTAUT2 constructs influence LLM adoption differently across five SE purposes, with some factors showing negative effects when examined in isolation.
citing papers explorer
-
Assessing, Exploiting, and Mitigating Syntactic Robustness Failures in LLM-Based Code Generation
LLM code generation lacks syntactic robustness on math-formula prompts, but formula-reduction pre-processing raises it from 54.05% to 74.42%.
-
Exploring Individual Factors in the Adoption of LLMs for Specific Software Engineering Purposes
Survey of 188 engineers using SEM finds that UTAUT2 constructs influence LLM adoption differently across five SE purposes, with some factors showing negative effects when examined in isolation.