Refusal in LLMs is an Affine Function

Toy models of superposition

Original

Nelson Elhage, Tristan Hume, Catherine Olsson, Nicholas Schiefer, Tom Henighan, Shauna Kravec, Zac Hatfield-Dodds, Robert Lasenby, Dawn Drain, Carol Chen, et al · 2022

Earlier work this paper cites.

Qwen technical report

Original

Jinze Bai, Shuai Bai, Yunfei Chu, Zeyu Cui, Kai Dang, Xiaodong Deng, Yang Fan, Wenbin Ge, Yu Han, Fei Huang, et al · 2023

Earlier work this paper cites.

The linear representation hypothesis and the geometry of large language models

Original

Kiho Park, Yo Joong Choe, and Victor Veitch · 2023

Earlier work this paper cites.

Steering llama 2 via contrastive activation addition

Original

Nina Rimsky, Nick Gabrieli, Julian Schulz, Meg Tong, Evan Hubinger, and Alexander Matt Turner · 2023

Earlier work this paper cites.

Stanford alpaca: An instruction-following llama model

Rohan Taori, Ishaan Gulrajani, Tianyi Zhang, Yann Dubois, Xuechen Li, Carlos Guestrin, Percy Liang, and Tatsunori B. Hashimoto · 2023

Earlier work this paper cites.

Universal and transferable adversarial attacks on aligned language models, 2023

Original

Andy Zou, Zifan Wang, Nicholas Carlini, Milad Nasr, J. Zico Kolter, and Matt Fredrikson · 2023

Cited alongside, same era.

Refusal in language models is mediated by a single direction

Original

Andy Arditi, Oscar Obeso, Aaquib Syed, Daniel Paleka, Nina Rimsky, Wes Gurnee, and Neel Nanda · 2024

Cited alongside, same era.

Leace: Perfect linear concept erasure in closed form

Nora Belrose, David Schneider-Joseph, Shauli Ravfogel, Ryan Cotterell, Edward Raff, and Stella Biderman · 2024

Cited alongside, same era.

The llama 3 herd of models

Original

Abhimanyu Dubey, Abhinav Jauhri, Abhinav Pandey, Abhishek Kadian, Ahmad Al-Dahle, Aiesha Letman, Akhil Mathur, Alan Schelten, Amy Yang, Angela Fan, et al · 2024

Cited alongside, same era.

Does transformer interpretability transfer to rnns?, 2024

Original

Gonçalo Paulo, Thomas Marshall, and Nora Belrose · 2024

Closest in time.

Eagle and finch: Rwkv with matrix-valued states and dynamic recurrence

Original

Bo Peng, Daniel Goldstein, Quentin Anthony, Alon Albalak, Eric Alcaide, Stella Biderman, Eugene Cheah, Teddy Ferdinan, Haowen Hou, Przemysław Kazienko, et al · 2024

Closest in time.

Gemma: Open models based on gemini research and technology

Original

Gemma Team, Thomas Mesnard, Cassidy Hardin, Robert Dadashi, Surya Bhupatiraju, Shreya Pathak, Laurent Sifre, Morgane Rivière, Mihir Sanjay Kale, Juliette Love, et al · 2024

Closest in time.

Yi: Open foundation models by 01. ai

Original

Alex Young, Bei Chen, Chao Li, Chengen Huang, Ge Zhang, Guanwei Zhang, Heng Li, Jiangcheng Zhu, Jianqun Chen, Jing Chang, et al · 2024

Closest in time.