# Steering Language Models with Weight Arithmetic

arXiv: https://arxiv.org/abs/2511.05408 · HTML: https://mlsanity.com/paper/2511.05408/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- Builds on 42 of its 50 references that are in the map.
- First posted on arXiv 7 Nov 2025.

## Builds on (most cited first, 30 of 42)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding](https://mlsanity.com/paper/1804.07461/) (2018)
- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [On the Opportunities and Risks of Foundation Models](https://mlsanity.com/paper/2108.07258/) (2021)
- [Finetuned Language Models Are Zero-Shot Learners](https://mlsanity.com/paper/2109.01652/) (2021)
- [TruthfulQA: Measuring How Models Mimic Human Falsehoods](https://mlsanity.com/paper/2109.07958/) (2021)
- [TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension](https://mlsanity.com/paper/1705.03551/) (2017)
- [Inference-Time Intervention: Eliciting Truthful Answers from a Language Model](https://mlsanity.com/paper/2306.03341/) (2023)
- [Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!](https://mlsanity.com/paper/2310.03693/) (2023)
- [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)
- [A General Language Assistant as a Laboratory for Alignment](https://mlsanity.com/paper/2112.00861/) (2021)
- [Towards Understanding Sycophancy in Language Models](https://mlsanity.com/paper/2310.13548/) (2023)
- [Refusal in Language Models Is Mediated by a Single Direction](https://mlsanity.com/paper/2406.11717/) (2024)
- [Steering Language Models With Activation Engineering](https://mlsanity.com/paper/2308.10248/) (2023)
- [Discovering Language Model Behaviors with Model-Written Evaluations](https://mlsanity.com/paper/2212.09251/) (2022)
- [TIES-Merging: Resolving Interference When Merging Models](https://mlsanity.com/paper/2306.01708/) (2023)
- [Confounding variables can degrade generalization performance of radiological deep learning models](https://mlsanity.com/paper/1807.00431/) (2018)
- [Alignment faking in large language models](https://mlsanity.com/paper/2412.14093/) (2024)
- [Persona Vectors: Monitoring and Controlling Character Traits in Language Models](https://mlsanity.com/paper/2507.21509/) (2025)
- [tinyBenchmarks: evaluating LLMs with fewer examples](https://mlsanity.com/paper/2402.14992/) (2024)
- [A Long Way to Go: Investigating Length Correlations in RLHF](https://mlsanity.com/paper/2310.03716/) (2023)
- [Extracting Latent Steering Vectors from Pretrained Language Models](https://mlsanity.com/paper/2205.05124/) (2022)
- [Analyzing the Generalization and Reliability of Steering Vectors](https://mlsanity.com/paper/2407.12404/) (2024)
- [Model Breadcrumbs: Scaling Multi-Task Model Merging with Sparse Masks](https://mlsanity.com/paper/2312.06795/) (2023)
- [Localizing Task Information for Improved Model Merging and Compression](https://mlsanity.com/paper/2405.07813/) (2024)

## Built on by (most cited first, 20 of 20)

- [Why Steering Works: Toward a Unified View of Language Model Parameter Dynamics](https://mlsanity.com/paper/2602.02343/) (2026)
- [Large Language Models Generate Harmful Responses Using a Distinct Mechanism, Shared Across Harm Types](https://mlsanity.com/paper/2604.09544/) (2026)
- [Mechanistically Eliciting Latent Behaviors in Language Models](https://mlsanity.com/paper/2606.29604/) (2026)
- [AI Steerability 360: A Toolkit for Steering Large Language Models](https://mlsanity.com/paper/2603.07837/) (2026)
- [Overtrained, Not Misaligned](https://mlsanity.com/paper/2605.12199/) (2026)
- [Decomposing how prompting steers behavior](https://mlsanity.com/paper/2606.03093/) (2026)
- [CreativityNeuro: Steering Language Model Weights to Improve Divergent Thinking and Reduce Mode Collapse](https://mlsanity.com/paper/2607.01433/) (2026)
- [C-DeltaTheta: Circuit-Restricted Weight Arithmetic for Selective Refusal](https://mlsanity.com/paper/2602.04521/) (2026)
- [The GRADIEND Python Package: An End-to-End System for Gradient-Based Feature Learning](https://mlsanity.com/paper/2602.23993/) (2026)
- [Distilling Linearized Behavior into Non-Linear Fine-Tuning for Effective Task Arithmetic](https://mlsanity.com/paper/2605.18993/) (2026)
- [Overthinking: Amplifying Reasoning Weights to Extract Learned Secrets](https://mlsanity.com/paper/2607.08173/) (2026)
- [Watch the Model Think: On-Policy Extraction of Activation Steering Vectors](https://mlsanity.com/paper/2602.14143/) (2026)
- [DeCoVec: Building Decoding Space based Task Vector for Large Language Models via In-Context Learning](https://mlsanity.com/paper/2604.11129/) (2026)
- [Trait-space Monitoring for Emergent Misalignment During Supervised Finetuning](https://mlsanity.com/paper/2606.07631/) (2026)
- [Functional and Secure Code Generation with Task Vectors](https://mlsanity.com/paper/2607.07881/) (2026)
- [Policy Gradient Steering: Interventions from Behavioral Objectives](https://mlsanity.com/paper/2607.27574/) (2026)
- [The Halt Vector: Internalizing a Causal Steering Intervention for Efficient Reasoning](https://mlsanity.com/paper/2608.28859/) (2026)
- [Steering Under Compression: Dose-Response, Capability Cost, and Failure Asymmetry in Quantized LLMs](https://mlsanity.com/paper/2609.06473/) (2026)
- [Training-Free Task Vectors for LLM Behavioral Control](https://mlsanity.com/paper/2609.09054/) (2026)
- [Weights Read and Write Features: Scalable Parameter Decomposition Grounded in Activation Space](https://mlsanity.com/paper/2609.37731/) (2026)

## Abstract (arXiv)

Providing high-quality feedback to Large Language Models (LLMs) on a diverse training distribution can be difficult and expensive, and providing feedback only on a narrow distribution can result in unintended generalizations. To better leverage narrow training data, we propose contrastive weight steering, a simple post-training method that edits the model parameters using weight arithmetic. We isolate a behavior direction in weight-space by subtracting the weight deltas from two small fine-tunes -- one that induces the desired behavior and another that induces its opposite -- and then add or remove this direction to modify the model's weights. We apply this technique to mitigate sycophancy and induce misalignment, and find that weight steering often generalizes further than activation steering, achieving stronger out-of-distribution behavioral control before degrading general capabilities. We also show that, in the context of task-specific fine-tuning, weight steering can partially mitigate undesired behavioral drift: it can reduce sycophancy and under-refusals introduced during fine-tuning while preserving task performance gains. Finally, we provide preliminary evidence that emergent misalignment can be detected by measuring the similarity between fine-tuning updates and an "evil" weight direction, suggesting that it may be possible to monitor the evolution of weights during training and detect rare misaligned behaviors that never manifest during training or evaluations.