AI Steerability 360: A Toolkit for Steering Large Language Models
Not on the map. Why?
Abstract (arXiv)
The AI Steerability 360 toolkit is an extensible, open-source Python library for steering LLMs. Steering abstractions are designed around four model control surfaces: input (modification of the prompt), structural (modification of the model's weights or architecture), state (modification of the model's activations and attentions), and output (modification of the decoding or generation process). Steering methods exert control on the model through a common interface, termed a steering pipeline, which additionally allows for the composition of multiple steering methods. Comprehensive evaluation and comparison of steering methods/pipelines is facilitated by use case classes (for defining tasks) and a benchmark class (for performance comparison on a given task). The functionality provided by the toolkit significantly lowers the barrier to developing and comprehensively evaluating steering methods. The toolkit is Hugging Face native and is released under an Apache 2.0 license at https://github.com/IBM/AISteer360.
Key facts. Cited by 2 papers in the map (data through 13 Oct 2026). Builds on 30 of its 42 references that are in the map. First posted on arXiv 8 Mar 2026.
Builds on
30 of 42 references.
References · 30
- 2020Language Models are Few-Shot Learnerscited by 32,320
- 2021TruthfulQA: Measuring How Models Mimic Human Falsehoodscited by 2,949
- 2022Locating and Editing Factual Associations in GPTcited by 2,650
- 2024LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Modelscited by 1,450
- 2023Inference-Time Intervention: Eliciting Truthful Answers from a Language Modelcited by 1,280
- 2023Steering Llama 2 via Contrastive Activation Additioncited by 1,042
- 2022Large Language Models Are Human-Level Prompt Engineerscited by 1,031
- 2022Discovering Language Model Behaviors with Model-Written Evaluationscited by 824
- 2019Plug and Play Language Models: A Simple Approach to Controlled Text Generationcited by 797
- 2021DExperts: Decoding-Time Controlled Text Generation with Experts and Anti-Expertscited by 437
- 2020GeDi: Generative Discriminator Guided Sequence Generationcited by 378
- 2021FUDGE: Controlled Text Generation With Future Discriminatorscited by 375
18 more
- 2023In-context Vectors: Making In Context Learning More Effective and Controllable Through Latent Space Steeringcited by 243
- 2024Programming Refusal with Conditional Activation Steeringcited by 200
- 2023Tell Your Model Where to Attend: Post-hoc Attention Steering for LLMscited by 87
- 2023Reward-Augmented Decoding: Efficient Controlled Text Generation With a Unidirectional Reward Modelcited by 79
- 2024pyvene: A Library for Understanding and Improving PyTorch Models via Interventionscited by 54
- 2025Angular Steering: Behavior Control via Rotation in Activation Spacecited by 47
- 2024Multi-property Steering of Large Language Models with Dynamic Activation Compositioncited by 38
- 2025One-shot Optimized Steering Vectors Mediate Safety-relevant Behaviors in LLMscited by 28
- 2024Evaluating the Prompt Steerability of Large Language Modelscited by 27
- 2025Steering Language Models with Weight Arithmeticcited by 20
- 2025EasySteer: A Unified Framework for High-Performance and Extensible LLM Steeringcited by 13
- 2024Large Language Models can be Strong Self-Detoxifierscited by 7
- 2025A Course Correction in Steerability Evaluation: Revealing Miscalibration and Side Effects in LLMscited by 7
- 2026Steer2Adapt: Dynamically Composing Steering Vectors Elicits Efficient Adaptation of LLMscited by 7
- 2025What's Producible May Not Be Reachable: Measuring the Steerability of Generative Modelscited by 6
- 2025Dialz: A Python Toolkit for Steering Vectorscited by 4
- 2026vLLM Hook v0: A Plug-in for Programming Model Internals on vLLMcited by 4
- 2023Function Composition in Trustworthy Machine Learning: Implementation Choices, Insights, and Questionscited by 1
Built on by
Citing papers per year: 2026: 2.
2 papers.