Circuits of LLM Classifiers

Paper recorded by Signals 4 on 2026-10-21 in cs.LG. Abstract reproduced from arXiv; link to the original below.

Published 2026-10-21 on arXiv · recorded by Signals 4 on 2026-10-22

Category: cs.LG · 机器学习 · first seen 2026-10-22

Abstract

Language models make it easy to build classifiers by simply prompting a model with the sample to classify. However, their predictions are neither deterministic nor uniformly reliable across samples. How can we combine predictions from different models to improve reliability? We view LLM classifiers as noisy measurement instruments of an underlying target label. Our goal is to maximize average clas

Read on arXiv →