Modelpedia
Work in progress
About
Findings
Models
Concepts
Methods
Datasets
Sources
Light
Dark
Do LLMs ``know'' internally when they follow instructions?
2025-01-22
· ICLR 2025 Poster ·
anchor
Findings
IC-493
A linear direction in the input embedding space of Llama-2-7B-Chat, Llama-2-13B-Chat, Mistral-7B-Instruct-v0.3, and Phi-3-mini-128k predicts instruction-following success, generalizes across tasks but not instruction types, and can be used to improve adherence via representation engineering
IC-494
The instruction-following dimension in Llama-2-7B-Chat and Llama-2-13B-Chat is more closely aligned with prompt phrasing than with task familiarity or instruction difficulty