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.
@article{arxiv.2409.19001,
title = {Pay Attention to What Matters},
author = {Pedro Luiz Silva and Antonio de Domenico and Ali Maatouk and Fadhel Ayed},
journal= {arXiv preprint arXiv:2409.19001},
year = {2024}
}