1 citations · 1 across the 10 of their papers we have counts for
3 papers · 1 filter
Diff Mining: Logit Differences Reveal Finetuning Objectives
Greg Kocher, Robert West, Clément Dumas +1
Finetuning has become the gold standard for refining existing behaviors and inducing new ones in language models, yet it often remains unclear exactly which behaviors emerge during…
Synthetic Persona Pretraining: Alignment from Token Zero
Julian Minder, Viktor Moskvoretskii, Raghav Singhal +12
As language-model-based AI is increasingly deployed in autonomous settings, aligning its goals and values with those of humans becomes critical. Today, alignment, and the assistant…
Activation Oracles: Training and Evaluating LLMs as General-Purpose Activation Explainers
Adam Karvonen, James Chua, Clément Dumas +8
Large language model (LLM) activations are notoriously difficult to understand, with most existing techniques using complex, specialized methods for interpreting them. Recent work…