Saved in:
Bibliographic Details
Main Authors: Silva, Pedro Luiz, de Domenico, Antonio, Maatouk, Ali, Ayed, Fadhel
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2409.19001
Tags: Add Tag
No Tags, Be the first to tag this record!
Table of Contents:
  • Despite the remarkable success of Large Language Models (LLMs), they still exhibit a limited capability to align their outputs to the user instructions. In this work, we introduce a simple and effective method, which we name GUIDE, that mechanistically increases attention scores in instruction tokens. To support this operation, we present Influence, a novel metric that highlights how the user's instructions propagate through the transformer layers and impact the LLM output. Our results show that GUIDE improves the accuracy of following instructions 29.4 % to 60.4%, outperforming natural prompting alternatives and Supervised Fine-Tuning up to 1M tokens.