Modelpedia
Work in progress
About
Findings
Models
Concepts
Methods
Datasets
Sources
Light
Dark
How new data permeates LLM knowledge and how to dilute it
2025-01-22
· ICLR 2025 Spotlight ·
anchor
Findings
IC-214
In-context learning of an outlandish sample produces a much diminished keyword-probability-to-priming relationship compared to in-weight gradient learning in Palm-2