ReFT: Representation Finetuning for Language Models
Paper
•
2404.03592
•
Published
•
100
Aryaman Arora
aryaman
LookLikeSquareButItRectangle's profile picture
juliekallini's profile picture
eliebak's profile picture
·
AI & ML interests
AI, mechanistic interpretability, South Asian languages
Organizations
authored
4
papers
over 1 year ago
CausalGym: Benchmarking causal interpretability methods on linguistic tasks
Paper
•
2402.12560
•
Published
•
3
IruMozhi: Automatically classifying diglossia in Tamil
Paper
•
2311.07804
•
Published
A Reply to Makelov et al. (2023)'s "Interpretability Illusion" Arguments
Paper
•
2401.12631
•
Published