Lanna Project · Progress Measured 2026-05-18
Latest result

A step forward.

+20%
Translation fidelity over the off-the-shelf base

The latest model adapter listens to Northern Thai more faithfully than the base model — by a clear margin.

A snapshot · Lanna benchmark, May 2026

Improvement over base model
3 iterations

Northern Thai → Standard Thai · held-out conversational text

Base model · off-the-shelf
0%
A capable general-purpose Thai LLM, used as-is. Handles Standard Thai well; stumbles on Northern Thai vocabulary, particles, and tone.
First adapter · 2026-05-08
+13%
Lightweight adaptation on the natural-conversation slice of the corpus — the model begins to hear Northern Thai as Northern Thai.
Latest adapter · 2026-05-18 Current
+20%
Retrained on a refined dataset with a tuned recipe — recovers earlier failure cases like repetition loops and dropped dialect particles.