8 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…
The Effectiveness of Approximate Regularized Replay for Efficient Supervised Fine-Tuning of Large Language Models
Matthew Riemer, Erik Miehling, Miao Liu +2
Although parameter-efficient fine-tuning methods, such as LoRA, only modify a small subset of parameters, they can have a significant impact on the model. Our instruction-tuning ex…
The Ultimate Test of Superintelligent AI Agents: Can an AI Balance Care and Control in Asymmetric Relationships?
Djallel Bouneffouf, Matthew Riemer, Kush Varshney
This paper introduces the Shepherd Test, a new conceptual test for assessing the moral and relational dimensions of superintelligent artificial agents. The test is inspired by huma…
Position: Theory of Mind Benchmarks are Broken for Large Language Models
Matthew Riemer, Zahra Ashktorab, Djallel Bouneffouf +4
Our paper argues that the majority of theory of mind benchmarks are broken because of their inability to directly test how large language models (LLMs) adapt to new partners. This…
Combining Domain and Alignment Vectors to Achieve Better Knowledge-Safety Trade-offs in LLMs
Megh Thakkar, Quentin Fournier, Matthew Riemer +4
There is a growing interest in training domain-expert LLMs that excel in specific technical fields compared to their general-purpose instruction-tuned counterparts. However, these…
Agentic AI Needs a Systems Theory
Erik Miehling, Karthikeyan Natesan Ramamurthy, Kush R. Varshney +11
The endowment of AI with reasoning capabilities and some degree of agency is widely viewed as a path toward more capable and generalizable systems. Our position is that the current…