1 citations · 1 across the 3 of their papers we have counts for
3 papers
Decomposing Refusal Steering in Mixture-of-Experts Models
Anna C. Marbut, Daniel R. Olson, Travis J. Wheeler
Safety alignment in instruction-tuned large language models (LLMs) depends on a model's ability to reliably refuse harmful or disallowed requests. Recent work has shown that a stee…
Exploring the Impact of a Transformer's Latent Space Geometry on Downstream Task Performance
Anna C. Marbut, John W. Chandler, Travis J. Wheeler
It is generally thought that transformer-based large language models benefit from pre-training by learning generic linguistic knowledge that can be focused on a specific task durin…
Reliable Measures of Spread in High Dimensional Latent Spaces
Anna C. Marbut, Katy McKinney-Bock, Travis J. Wheeler
Understanding geometric properties of natural language processing models' latent spaces allows the manipulation of these properties for improved performance on downstream tasks. On…