TaiwanEval
non-profit
AI & ML interests
Reproducible, programmatically generated LLM benchmarks for Taiwan: rule-grounded evaluation, error attribution, calibration, and local quantized inference. Home of LaborCalc-TW.
No public activity
Reproducible, programmatically generated LLM benchmarks for Taiwan: rule-grounded evaluation, error attribution, calibration, and local quantized inference. Home of LaborCalc-TW.
No public activity