From 246cbdffa70846fc140e57fadb709990b1da9aff Mon Sep 17 00:00:00 2001 From: Steven Abreu Date: Mon, 4 Nov 2024 10:19:53 +0100 Subject: [PATCH] Add conceptor steering paper (MINT@NeurIPS 2024) --- README.md | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/README.md b/README.md index 9de9485..556d865 100644 --- a/README.md +++ b/README.md @@ -94,6 +94,11 @@ Also: ### Steering vectors +- [Steering Large Language Models using Conceptors: Improving Addition-Based Activation Engineering](https://arxiv.org/abs/2410.16314) + - Author(s): Joris Postmus, Steven Abreu + - Date: 2024-10 + - Venue: NeurIPS 2024 ([Workshop on Foundation Model Interventions](https://sites.google.com/view/mint-2024/home)) + - Code: - - [Analyzing the Generalization and Reliability of Steering Vectors](https://arxiv.org/abs/2407.12404) - Author(s): Daniel Tan, David Chanin, Aengus Lynch, Dimitrios Kanoulas, Brooks Paige, Adria Garriga-Alonso, Robert Kirk - Date: 2024-07