llm-validation

This paper presents a mixed-method survey and expert interview study examining how LLM-based validation tools can help organizations translate EU AI Act obligations into testable, auditable requirements and evidence artifacts.

This paper presents SynthAVE, a large-scale human-validated benchmark for attribute value extraction in e-commerce, using a multi-LLM arena framework with 21 judge configurations to validate synthetic labels efficiently and cost-effectively while maintaining quality parity with human review.