Metric-Construction Coupling Inflates Measured Synthetic Dialect Recovery
arXiv:2610.00164v1 Announce Type: new Abstract: Korean dialect corpora are available but not redistributable: weights may be released, while reproducing training and evaluation from the underlying data cannot be. We ask how much of that supervision synthetic data recovers, and whether that recovery…
Read the full story at arXiv cs.CL ↗
Timeline · 1 report
- 2026-10-02 04:00 · arXiv cs.CL
Metric-Construction Coupling Inflates Measured Synthetic Dialect Recovery