Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
Do Models Read What They Write? Causal Registers in Scratchpad Reasoning
Benjamin Shih, John Winnicki, Eric Darve
A central hope behind process supervision is that models can expose intermediate variables that matter for their later behavior. For this to help with alignment, a scratchpad must…
cs.LG2025
SD-KDE: Score-Debiased Kernel Density Estimation
Elliot L. Epstein, Rajat Dwaraknath, Thanawat Sornwanee +2
We propose a novel method for density estimation that leverages an estimated score function to debias kernel density estimation (SD-KDE). In our approach, each data point is adjust…