Researchers · Interviewed at COLM 2026

Christina Baek

Carnegie Mellon University / DatologyAI

COLM 2026 in San Francisco. Are You Wasting Your Fine-Tuning Data? Why It Belongs in Pretraining

COLM 2026 · October 7, 2026 · 23 min

COLM 2026 in San Francisco. Are You Wasting Your Fine-Tuning Data? Why It Belongs in Pretraining

Most teams with a small domain dataset follow the standard recipe: pretrain a general model, then fine-tune on the domain data. Christina Baek's results suggest that recipe leaves performance on the table.

Work is presented at COLM 2026 (the Third Annual Conference on Language Modeling).

More from COLM 2026

All event interviews →