GenFair generates diverse source test cases via equivalence partitioning, mutation, and boundary value analysis, then applies metamorphic relations and tone comparison to flag fairness faults, claiming higher fault detection rates than template-based and grammar-based baselines.
Metamorphic testing and certified mitigation of fairness violations in nlp models
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
baseline 1
citation-polarity summary
fields
cs.SE 1years
2025 1verdicts
REJECT 1roles
baseline 1polarities
baseline 1representative citing papers
citing papers explorer
-
GenFair: Systematic Test Generation for Fairness Fault Detection in Large Language Models
GenFair generates diverse source test cases via equivalence partitioning, mutation, and boundary value analysis, then applies metamorphic relations and tone comparison to flag fairness faults, claiming higher fault detection rates than template-based and grammar-based baselines.