# Transmuting prompts into weights

arXiv: https://arxiv.org/abs/2510.08734 · HTML: https://mlsanity.com/paper/2510.08734/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 34 of its 41 references that are in the map.
- First posted on arXiv 9 Oct 2025.

## Builds on (most cited first, 30 of 34)

- [Locating and Editing Factual Associations in GPT](https://mlsanity.com/paper/2202.05262/) (2022)
- [GLU Variants Improve Transformer](https://mlsanity.com/paper/2002.05202/) (2020)
- [Transformer Feed-Forward Layers Are Key-Value Memories](https://mlsanity.com/paper/2012.14913/) (2020)
- [Editing Models with Task Arithmetic](https://mlsanity.com/paper/2212.04089/) (2022)
- [Steering Llama 2 via Contrastive Activation Addition](https://mlsanity.com/paper/2312.06681/) (2023)
- [Steering Language Models With Activation Engineering](https://mlsanity.com/paper/2308.10248/) (2023)
- [Transformers learn in-context by gradient descent](https://mlsanity.com/paper/2212.07677/) (2022)
- [What Can Transformers Learn In-Context? A Case Study of Simple Function Classes](https://mlsanity.com/paper/2208.01066/) (2022)
- [What learning algorithm is in-context learning? Investigations with linear models](https://mlsanity.com/paper/2211.15661/) (2022)
- [Editing Factual Knowledge in Language Models](https://mlsanity.com/paper/2104.08164/) (2021)
- [Fast Model Editing at Scale](https://mlsanity.com/paper/2110.11309/) (2021)
- [Persona Vectors: Monitoring and Controlling Character Traits in Language Models](https://mlsanity.com/paper/2507.21509/) (2025)
- [In-Context Learning Creates Task Vectors](https://mlsanity.com/paper/2310.15916/) (2023)
- [Function Vectors in Large Language Models](https://mlsanity.com/paper/2310.15213/) (2023)
- [In-context Vectors: Making In Context Learning More Effective and Controllable Through Latent Space Steering](https://mlsanity.com/paper/2311.06668/) (2023)
- [Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications](https://mlsanity.com/paper/2402.05162/) (2024)
- [Extracting Latent Steering Vectors from Pretrained Language Models](https://mlsanity.com/paper/2205.05124/) (2022)
- [Why Can GPT Learn In-Context? Language Models Implicitly Perform Gradient Descent as Meta-Optimizers](https://mlsanity.com/paper/2212.10559/) (2022)
- [Analyzing the Generalization and Reliability of Steering Vectors](https://mlsanity.com/paper/2407.12404/) (2024)
- [Improving Steering Vectors by Targeting Sparse Autoencoder Features](https://mlsanity.com/paper/2411.02193/) (2024)
- [Transformers Implement Functional Gradient Descent to Learn Non-Linear Functions In Context](https://mlsanity.com/paper/2312.06528/) (2023)
- [A Unified Understanding and Evaluation of Steering Methods](https://mlsanity.com/paper/2502.02716/) (2025)
- [Learning without training: The implicit dynamics of in-context learning](https://mlsanity.com/paper/2507.16003/) (2025)
- [Towards Reliable Evaluation of Behavior Steering Interventions in LLMs](https://mlsanity.com/paper/2410.17245/) (2024)
- [Model Editing as a Robust and Denoised variant of DPO: A Case Study on Toxicity](https://mlsanity.com/paper/2405.13967/) (2024)
- [Task Vectors in In-Context Learning: Emergence, Formation, and Benefit](https://mlsanity.com/paper/2501.09240/) (2025)
- [Comparing Bottom-Up and Top-Down Steering Approaches on In-Context Learning Tasks](https://mlsanity.com/paper/2411.07213/) (2024)
- [Distributional Associations vs In-Context Reasoning: A Study of Feed-forward and Attention Layers](https://mlsanity.com/paper/2406.03068/) (2024)
- [Implicit In-context Learning](https://mlsanity.com/paper/2405.14660/) (2024)
- [Learning Task Representations from In-Context Learning](https://mlsanity.com/paper/2502.05390/) (2025)

## Built on by (most cited first, 3 of 3)

- [Equivalence of Context and Parameter Updates in Modern Transformer Blocks](https://mlsanity.com/paper/2511.17864/) (2025)
- [PatchKV: Weight-Space Compensation of KV Cache](https://mlsanity.com/paper/2609.39329/) (2026)
- [When Can Prefixes Compile LoRA? Exact Resource-Capped Tests for Frozen Attention](https://mlsanity.com/paper/2609.36766/) (2026)

## Abstract (arXiv)

A growing body of research has demonstrated that the behavior of large language models can be effectively controlled at inference time by directly modifying their internal states, either through vector additions to their activations or through updates to their weight matrices. These techniques, while powerful, are often guided by empirical heuristics, such as deriving ``steering vectors'' from the average activations of contrastive prompts. Building on the foundational work of Dherin et al. (2025), who discovered that a prompt's influence mathematically maps to token-dependent implicit weight updates and introduced the initial concept of a static thought patch for prompt compression, we elevate this framework into a robust algorithm for direct model editing. We derive a principled method for condensing this transient information into token-independent thought vectors and thought matrices. These constructs provide a theoretical explanation for existing vector-and-matrix-based model editing techniques and offer a direct, computationally-grounded method for transmuting textual input into reusable weight updates for complex architectures and new knowledge injection.