Ensemble based approach to quantifying uncertainty of LLM based classifications
Artificial Intelligence
2025-02-20 v2
Abstract
The output of Large Language Models (LLMs) are a function of the internal model's parameters and the input provided into the context window. The hypothesis presented here is that under a greedy sampling strategy the variance in the LLM's output is a function of the conceptual certainty embedded in the model's parametric knowledge, as well as the lexical variance in the input. Finetuning the model results in reducing the sensitivity of the model output to the lexical input variations. This is then applied to a classification problem and a probabilistic method is proposed for estimating the certainties of the predicted classes.
Cite
@article{arxiv.2502.08631,
title = {Ensemble based approach to quantifying uncertainty of LLM based classifications},
author = {Srijith Rajamohan and Ahmed Salhin and Josh Frazier and Rohit Kumar and Yu-Cheng Tsai and Todd Cook},
journal= {arXiv preprint arXiv:2502.08631},
year = {2025}
}