pith. sign in

Title resolution pending

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

fields

cs.SE 1

years

2026 1

verdicts

CONDITIONAL 1

representative citing papers

Defective Task Descriptions in LLM-Based Code Generation: Detection and Analysis

cs.SE · 2026-04-27 · conditional · novelty 6.0

SpecValidator detects lexical vagueness, under-specification, and syntax-formatting defects in LLM code-generation prompts with F1 0.804, outperforming GPT-5-mini and Claude Sonnet 4, and shows that under-specification is the most damaging defect type while richer benchmarks are more resilient.

citing papers explorer

Showing 1 of 1 citing paper.

  • Defective Task Descriptions in LLM-Based Code Generation: Detection and Analysis cs.SE · 2026-04-27 · conditional · none · ref 28

    SpecValidator detects lexical vagueness, under-specification, and syntax-formatting defects in LLM code-generation prompts with F1 0.804, outperforming GPT-5-mini and Claude Sonnet 4, and shows that under-specification is the most damaging defect type while richer benchmarks are more resilient.