Showing cs.CLShow all
2 papers · 1 filter
cs.CL2025
Incorporating Hierarchical Semantics in Sparse Autoencoder Architectures
Mark Muchane, Sean Richardson, Kiho Park +1
Sparse dictionary learning (and, in particular, sparse autoencoders) attempts to learn a set of human-understandable concepts that can explain variation on an abstract space. A bas…
cs.CL2024
RATE: Causal Explainability of Reward Models with Imperfect Counterfactuals
David Reber, Sean Richardson, Todd Nief +2
Reward models are widely used as proxies for human preferences when aligning or evaluating LLMs. However, reward models are black boxes, and it is often unclear what, exactly, they…