mlsanityData to 14 Oct 2026

Pay Attention to What Matters

arXiv 2409.19001 ↗First posted 19 Sep 2024cs.CL cs.AIcited by 1

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 16 of its 22 references that are in the map. First posted on arXiv 19 Sep 2024.

Builds on

16 of 22 references.

References · 16

  1. 2022Training language models to follow instructions with human feedbackcited by 15,971
  2. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
  3. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 8,065
  4. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,733
  5. 2019BERTScore: Evaluating Text Generation with BERTcited by 5,512
  6. 2022Locating and Editing Factual Associations in GPTcited by 2,691
  7. 2024SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineeringcited by 1,737
  8. 2024The AI Scientist: Towards Fully Automated Open-Ended Scientific Discoverycited by 1,071
  9. 2023Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formattingcited by 817
  10. 2020Quantifying Attention Flow in Transformerscited by 775
  11. 2023Towards Best Practices of Activation Patching in Language Models: Metrics and Methodscited by 359
  12. 2021Generic Attention-model Explainability for Interpreting Bi-Modal and Encoder-Decoder Transformerscited by 320
4 more
  1. 2023Black-Box Prompt Optimization: Aligning Large Language Models without Model Trainingcited by 122
  2. 2022On Decoding Strategies for Neural Text Generatorscited by 90
  3. 2024In Search of Needles in a 11M Haystack: Recurrent Memory Finds What LLMs Misscited by 36
  4. 2024Insights into LLM Long-Context Failures: When Transformers Know but Don't Tellcited by 36

Built on by

Cited by year

Citing papers per year: 2025: 1.

1 paper.

  1. 2025Prompting Decision Transformers for Zero-Shot Reach-Avoid Policiescited by 0