# Steer Model beyond Assistant: Controlling System Prompt Strength via Contrastive Decoding

arXiv: https://arxiv.org/abs/2601.06403 · HTML: https://mlsanity.com/paper/2601.06403/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 38 of its 54 references that are in the map.
- First posted on arXiv 10 Jan 2026.

## Builds on (most cited first, 30 of 38)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Constitutional AI: Harmlessness from AI Feedback](https://mlsanity.com/paper/2212.08073/) (2022)
- [Instruction-Following Evaluation for Large Language Models](https://mlsanity.com/paper/2311.07911/) (2023)
- [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)
- [Plug and Play Language Models: A Simple Approach to Controlled Text Generation](https://mlsanity.com/paper/1912.02164/) (2019)
- [Whose Opinions Do Language Models Reflect?](https://mlsanity.com/paper/2303.17548/) (2023)
- [Contrastive Decoding: Open-ended Text Generation as Optimization](https://mlsanity.com/paper/2210.15097/) (2022)
- [FUDGE: Controlled Text Generation With Future Discriminators](https://mlsanity.com/paper/2104.05218/) (2021)
- [Quantifying the Persona Effect in LLM Simulations](https://mlsanity.com/paper/2402.10811/) (2024)
- [Can LLM be a Personalized Judge?](https://mlsanity.com/paper/2406.11657/) (2024)
- [Stay on topic with Classifier-Free Guidance](https://mlsanity.com/paper/2306.17806/) (2023)
- [Flipping the Dialogue: Training and Evaluating User Language Models](https://mlsanity.com/paper/2510.06552/) (2025)
- [On the steerability of large language models toward data-driven personas](https://mlsanity.com/paper/2311.04978/) (2023)
- [SimBench: Benchmarking the Ability of Large Language Models to Simulate Human Behaviors](https://mlsanity.com/paper/2510.17516/) (2025)
- [Towards Reliable Evaluation of Behavior Steering Interventions in LLMs](https://mlsanity.com/paper/2410.17245/) (2024)
- [LLMs + Persona-Plug = Personalized LLMs](https://mlsanity.com/paper/2409.11901/) (2024)
- [AI PERSONA: Towards Life-long Personalization of LLMs](https://mlsanity.com/paper/2412.13103/) (2024)
- [Nudging: Inference-time Alignment of LLMs via Guided Decoding](https://mlsanity.com/paper/2410.09300/) (2024)
- [Localized Cultural Knowledge is Conserved and Controllable in Large Language Models](https://mlsanity.com/paper/2504.10191/) (2025)
- [Spectrum Tuning: Post-Training for Distributional Coverage and In-Context Steerability](https://mlsanity.com/paper/2510.06084/) (2025)
- [Learning to Make MISTAKEs: Modeling Incorrect Student Thinking And Key Errors](https://mlsanity.com/paper/2510.11502/) (2025)
- [The Potential and Challenges of Evaluating Attitudes, Opinions, and Values in Large Language Models](https://mlsanity.com/paper/2406.11096/) (2024)
- [Adaptive Contrastive Decoding in Retrieval-Augmented Generation for Handling Noisy Contexts](https://mlsanity.com/paper/2408.01084/) (2024)
- [ToxiCraft: A Novel Framework for Synthetic Generation of Harmful Information](https://mlsanity.com/paper/2409.14740/) (2024)
- [Know Your Audience: Do LLMs Adapt to Different Age and Education Levels?](https://mlsanity.com/paper/2312.02065/) (2023)
- [From Tarzan to Tolkien: Controlling the Language Proficiency Level of LLMs for Content Generation](https://mlsanity.com/paper/2406.03030/) (2024)
- [Navigating the Alignment-Calibration Trade-off: A Pareto-Superior Frontier via Model Merging](https://mlsanity.com/paper/2510.17426/) (2025)
- [When Personalization Meets Reality: A Multi-Faceted Analysis of Personalized Preference Learning](https://mlsanity.com/paper/2502.19158/) (2025)
- [Toward Safe and Human-Aligned Game Conversational Recommendation via Multi-Agent Decomposition](https://mlsanity.com/paper/2504.20094/) (2025)

## Built on by (most cited first, 2 of 2)

- [IHDec: Divergence-Steered Contrastive Decoding for Securing Multi-Turn Instruction Hierarchies](https://mlsanity.com/paper/2606.29960/) (2026)
- [DoubtLess: Training-Free Contrastive Decoding for Efficient Reasoning](https://mlsanity.com/paper/2610.18862/) (2026)

## Abstract (arXiv)

Large language models excel at complex instructions yet struggle to deviate from their helpful assistant persona, as post-training instills strong priors that resist conflicting instructions. We introduce system prompt strength, a training-free method that treats prompt adherence as a continuous control. By contrasting logits from target and default system prompts, we isolate and amplify the behavioral signal unique to the target persona by a scalar factor alpha. Across five diverse benchmarks spanning constraint satisfaction, behavioral control, pluralistic alignment, capability modulation, and stylistic control, our method yields substantial improvements: up to +8.5 strict accuracy on IFEval, +45pp refusal rate on OffTopicEval, and +13% steerability on Prompt-Steering. Our approach enables practitioners to modulate system prompt strength, providing dynamic control over model behavior without retraining.