5 papers
AI Steerability 360: A Toolkit for Steering Large Language Models
Erik Miehling, Karthikeyan Natesan Ramamurthy, Praveen Venkateswaran +10
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 (modifi…
Sparsity May Be All You Need: Sparse Random Parameter Adaptation
Jesus Rios, Pierre Dognin, Ronny Luss +1
Full fine-tuning of large language models for alignment and task adaptation has become prohibitively expensive as models have grown in size. Parameter-Efficient Fine-Tuning (PEFT)…
Programming Refusal with Conditional Activation Steering
Bruce W. Lee, Inkit Padhi, Karthikeyan Natesan Ramamurthy +4
LLMs have shown remarkable capabilities, but precisely controlling their response behavior remains challenging. Existing activation steering methods alter LLM behavior indiscrimina…
Evaluating the Prompt Steerability of Large Language Models
Erik Miehling, Michael Desmond, Karthikeyan Natesan Ramamurthy +5
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 ev…
Granite Guardian
Inkit Padhi, Manish Nagireddy, Giandomenico Cornacchia +20
We introduce the Granite Guardian models, a suite of safeguards designed to provide risk detection for prompts and responses, enabling safe and responsible use in combination with…