📢Curious why your LLM behaves strangely after long SFT or DPO?
We offer a fresh perspective—consider doing a "force analysis" on your model’s behavior.
Check out our #ICLR2025 Oral paper:
Learning Dynamics of LLM Finetuning!
(0/12)
Yi (Joshua) Ren
@joshuaren.bsky.social
83 followers 4 following 21 posts
Ph.D. student @cs.ubc.ca, working on ML (learning dynamics, simplicity bias, iterated learning, LLM) joshua-ren.github.io