NodeSynth creates evidence-based synthetic queries via a taxonomy generator to evaluate LLMs, revealing up to 5x higher failure rates than human benchmarks and gaps in guard models.
Using synthetic data to improve the reproducibility of statistical results in psychological research.Psychological Methods, 29(4): 789, 2024
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
NodeSynth: Socially Aligned Synthetic Data for AI Evaluation
NodeSynth creates evidence-based synthetic queries via a taxonomy generator to evaluate LLMs, revealing up to 5x higher failure rates than human benchmarks and gaps in guard models.