My favorite papers

Some of my favorite papers.

Interpretability

A Mathematical Framework for Transformer Circuits
2021 · Elhage, et al.
Locating and Editing Factual Associations in GPT
2022 · Kevin Meng, David Bau, Alex Andonian, Yonatan Belinkov
Discovering Latent Knowledge in Language Models Without Supervision
2022 · Collin Burns, Haotian Ye, Dan Klein, Jacob Steinhardt

AI Safety

The Superintelligent Will
2012 · Nick Bostrom

Causality

On Pearl’s Hierarchy and the Foundations of Causal Inference
2021 · Elias Bareinboim, Juan D. Correa, Duligur Ibeling, Thomas Icard

Classics

A Neural Probabilistic Language Model
2003 · Yoshua Bengio, Réjean Ducharme, Pascal Vincent, Christian Jauvin
Attention is All You Need
2017 · Vaswani, et al.