paper-with-me

Papers

AI Steerability 360: A Toolkit for Steering Large Language Models

2026-03-08 · Erik Miehling, Karthikeyan Natesan Ramamurthy, Praveen Venkateswaran, Irene Ko, Pierre Dognin, Moninder Singh, Tejaswini Pedapati, Avinash Balakrishnan, Matthew Riemer, Dennis Wei, Inge Vejsbjerg, Elizabeth M. Daly, Kush R. Varshney 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.

📄 PDF Abstract BibTeX arXiv:2603.07837

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Evaluating the Prompt Steerability of Large Language Models

2024-11-19 · Erik Miehling, Michael Desmond, Karthikeyan Natesan Ramamurthy, Elizabeth M. Daly 외

Building pluralistic AI requires designing models that are able to be shaped to represent a wide range of value systems and cultures. Achieving this requires first being able to evaluate the degree to which a given model…

SteerEval: A Framework for Evaluating Steerability with Natural Language Profiles for Recommendation

2026-01-28 · Joyce Zhou, Weijie Zhou, Doug Turnbull, Thorsten Joachims arxiv

Natural-language user profiles have recently attracted attention not only for improved interpretability, but also for their potential to make recommender systems more steerable. By enabling direct editing, natural-langua…

When is Your LLM Steerable?

2026-06-10 · Chenrui Fan, Yize Cheng, Ming Li, Soheil Feizi 외 arxiv

Activation steering offers a lightweight approach to control language models' behavior at inference time, but whether it succeeds or fails heavily depends on the prompt, concept, model, and steering configuration. Findin…

What's Producible May Not Be Reachable: Measuring the Steerability of Generative Models

2025-03-21 · Keyon Vafa, Sarah Bentley, Jon Kleinberg, Sendhil Mullainathan

How should we evaluate the quality of generative models? Many existing metrics focus on a model's producibility, i.e. the quality and breadth of outputs it can generate. However, the actual value from using a generative …

Stiffness Optimization for Concentrated Bending in Magnetically Actuated Catheters: Maintaining Steerability under Gradient Stiffness

2026-05-24 · Jiewen Tan, Junnan Xue, Shing Shin Cheng, Shuang Song 외 arxiv

Achieving both efficient pushability (propulsion transmission) and proximally concentrated bending for steerability is challenging for magnetically actuated soft catheters: higher axial/bending stiffness improves force t…