Peter Chin

collaborators

2 papers

cs.CL2025

$K$ -MSHC: Unmasking Minimally Sufficient Head Circuits in Large Language Models with Experiments on Syntactic Classification Tasks

Pratim Chowdhary, Peter Chin, Deepernab Chakrabarty

Understanding which neural components drive specific capabilities in mid-sized language models ( $\leq$ 10B parameters) remains a key challenge. We introduce the $(K, ε)$ -Minimu…

cs.LG2022

Non-Volatile Memory Accelerated Posterior Estimation

Andrew Wood, Moshik Hershcovitch, Daniel Waddington +2

Bayesian inference allows machine learning models to express uncertainty. Current machine learning models use only a single learnable parameter combination when making predictions,…

K-MSHC: Unmasking Minimally Sufficient Head Circuits in Large Language Models with Experiments on Syntactic Classification Tasks

Non-Volatile Memory Accelerated Posterior Estimation

$K$ -MSHC: Unmasking Minimally Sufficient Head Circuits in Large Language Models with Experiments on Syntactic Classification Tasks