1 citations · 3 across the 11 of their papers we have counts for
Showing 2025 · cs.LGShow all
3 papers · 2 filters
cs.LG2025
How Well Can Preference Optimization Generalize Under Noisy Feedback?
Shawn Im, Sharon Li
As large language models (LLMs) advance their capabilities, aligning these models with human preferences has become crucial. Preference optimization, which trains models to disting…
cs.LG2025
Towards Interpretability Without Sacrifice: Faithful Dense Layer Decomposition with Mixture of Decoders
James Oldfield, Shawn Im, Sharon Li +3
Multilayer perceptrons (MLPs) are an integral part of large language models, yet their dense representations render them difficult to understand, edit, and steer. Recent methods le…
cs.LG2025★ 1 cited
A Unified Understanding and Evaluation of Steering Methods
Shawn Im, Sharon Li
Latent space steering methods provide a practical approach to controlling large language models by applying steering vectors to intermediate activations, guiding outputs toward des…