# EasySteer: A Unified Framework for High-Performance and Extensible LLM Steering

arXiv: https://arxiv.org/abs/2509.25175 · HTML: https://mlsanity.com/paper/2509.25175/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 44 references that are in the map.
- First posted on arXiv 29 Sep 2025.

## Builds on (most cited first, 22 of 22)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [Measuring Mathematical Problem Solving With the MATH Dataset](https://mlsanity.com/paper/2103.03874/) (2021)
- [Let's Verify Step by Step](https://mlsanity.com/paper/2305.20050/) (2023)
- [TruthfulQA: Measuring How Models Mimic Human Falsehoods](https://mlsanity.com/paper/2109.07958/) (2021)
- [Locating and Editing Factual Associations in GPT](https://mlsanity.com/paper/2202.05262/) (2022)
- [BLEURT: Learning Robust Metrics for Text Generation](https://mlsanity.com/paper/2004.04696/) (2020)
- [Refusal in Language Models Is Mediated by a Single Direction](https://mlsanity.com/paper/2406.11717/) (2024)
- [Mass-Editing Memory in a Transformer](https://mlsanity.com/paper/2210.07229/) (2022)
- [Steering Language Models With Activation Engineering](https://mlsanity.com/paper/2308.10248/) (2023)
- [Parameter-Efficient Fine-Tuning for Large Models: A Comprehensive Survey](https://mlsanity.com/paper/2403.14608/) (2024)
- [Persona Vectors: Monitoring and Controlling Character Traits in Language Models](https://mlsanity.com/paper/2507.21509/) (2025)
- [Programming Refusal with Conditional Activation Steering](https://mlsanity.com/paper/2409.05907/) (2024)
- [ReFT: Representation Finetuning for Language Models](https://mlsanity.com/paper/2404.03592/) (2024)
- [Personalized Steering of Large Language Models: Versatile Steering Vectors Through Bi-directional Preference Optimization](https://mlsanity.com/paper/2406.00045/) (2024)
- [Do I Know This Entity? Knowledge Awareness and Hallucinations in Language Models](https://mlsanity.com/paper/2411.14257/) (2024)
- [Word Embeddings Are Steers for Language Models](https://mlsanity.com/paper/2305.12798/) (2023)
- [Steering MoE LLMs via Expert (De)Activation](https://mlsanity.com/paper/2509.09660/) (2025)
- [Improving Reasoning Performance in Large Language Models via Representation Engineering](https://mlsanity.com/paper/2504.19483/) (2025)
- [Fractional Reasoning via Latent Steering Vectors Improves Inference Time Compute](https://mlsanity.com/paper/2506.15882/) (2025)
- [Causal Language Control in Multilingual Transformers via Sparse Feature Steering](https://mlsanity.com/paper/2507.13410/) (2025)
- [Steering Large Language Models to Evaluate and Amplify Creativity](https://mlsanity.com/paper/2412.06060/) (2024)

## Built on by (most cited first, 13 of 13)

- [Seeing but Not Thinking: Routing Distraction in Multimodal Mixture-of-Experts](https://mlsanity.com/paper/2604.08541/) (2026)
- [Internalizing LLM Reasoning via Discovery and Replay of Latent Actions](https://mlsanity.com/paper/2602.04925/) (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)
- [Quantifying Self-Preservation Bias in Large Language Models](https://mlsanity.com/paper/2604.02174/) (2026)
- [RankGuide: Tensor-Rank-Guided Routing and Steering for Efficient Reasoning](https://mlsanity.com/paper/2604.16694/) (2026)
- [Multi-Adapter Representation Interventions via Energy Calibration](https://mlsanity.com/paper/2605.28722/) (2026)
- [xMIx: High-Performance Serving-Time Platform for Mechanistic Interpretability Apps](https://mlsanity.com/paper/2607.22595/) (2026)
- [Do Unified Multimodal Models Think in One Space? A Lens Through Cross-Branch Steering](https://mlsanity.com/paper/2607.26411/) (2026)
- [Toward Latent Language Model Skills Steering and Optimization: An Empirical Study](https://mlsanity.com/paper/2608.29459/) (2026)
- [SafeTune: A Unified Faithful Library for Auditing and Repairing Safety Drift in Fine-Tuned LLMs](https://mlsanity.com/paper/2609.22153/) (2026)
- [Thinking Leakage: A Causal Audit of NoThink Post-Training in Hybrid Reasoning Models](https://mlsanity.com/paper/2609.28682/) (2026)
- [Efficient Reasoning via Constrained Optimization in Latent Space](https://mlsanity.com/paper/2609.34181/) (2026)

## Abstract (arXiv)

Large language model (LLM) steering has emerged as a promising paradigm for controlling model behavior at inference time through targeted manipulation of hidden states, offering a lightweight alternative to expensive retraining. However, existing steering frameworks suffer from critical limitations: computational inefficiency, limited extensibility, and restricted functionality that hinder both research progress and practical deployment. We present EasySteer, a unified framework for high-performance, extensible LLM steering built on vLLM. Our system features modular architecture with pluggable interfaces for both analysis-based and learning-based methods, fine-grained parameter control, pre-computed steering vectors for eight application domains, and an interactive demonstration system. Through deep integration with vLLM's optimized inference engine, EasySteer achieves 10.8-22.3× speedup over existing frameworks. Extensive experiments demonstrate its effectiveness in overthinking mitigation, hallucination reduction, and other key applications. EasySteer transforms steering from research technique to production-ready capability, establishing critical infrastructure for deployable, controllable language models.