Cite
Notes
Only stored in your browser.
Attribution
Found in the Middle: Permutation Self-Consistency Improves Listwise Ranking in Large Language Models
arXiv 2023
What Do Llamas Really Think? Revealing Preference Biases in Language Model Representations
What the DAAM: Interpreting Stable Diffusion Using Cross Attention
arXiv 2022
from 3 papers
Jimmy Lin
Raphael Tang
Xinyu Zhang
Akshat Pandey
Gefei Yang
Karun Kumar
Linqing Liu
Pontus Stenetorp
Xueguang Ma
grad-student
Zhiying Jiang