通过增强指令词注意力，让大模型更准确理解用户指令。
Pay Attention to What Matters
- 直接提升指令词在注意力机制中的得分，强化模型对指令的感知。
- 指令遵循准确率提升29.4%至60.4%，优于自然提示和监督微调。
- 提出新指标Influence，可追踪指令在模型层间的传播影响。
尽管大型语言模型（LLMs）取得了显著成功，但其输出与用户指令之间的对齐能力仍有限。本文提出一种简单有效的方法GUIDE，通过机制化提升指令词的注意力分数来改善这一问题。为支持该操作，我们引入Influence这一新指标，用于揭示用户指令如何在Transformer各层中传播并影响模型输出。实验结果表明，GUIDE将指令遵循准确率从29.4%提升至60.4%，优于自然提示法和监督微调，在长达100万词的输入下依然表现优异。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。