Generalised Probabilistic Modelling and Improved Uncertainty Estimation in Comparative LLM-as-a-judge

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Fathullah, Yassir, Gales, Mark J. F.
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866916748365660160
author Fathullah, Yassir
Gales, Mark J. F.
author_facet Fathullah, Yassir
Gales, Mark J. F.
contents This paper explores generalised probabilistic modelling and uncertainty estimation in comparative LLM-as-a-judge frameworks. We show that existing Product-of-Experts methods are specific cases of a broader framework, enabling diverse modelling options. Furthermore, we propose improved uncertainty estimates for individual comparisons, enabling more efficient selection and achieving strong performance with fewer evaluations. We also introduce a method for estimating overall ranking uncertainty. Finally, we demonstrate that combining absolute and comparative scoring improves performance. Experiments show that the specific expert model has a limited impact on final rankings but our proposed uncertainty estimates, especially the probability of reordering, significantly improve the efficiency of systems reducing the number of needed comparisons by ~50%. Furthermore, ranking-level uncertainty metrics can be used to identify low-performing predictions, where the nature of the probabilistic model has a notable impact on the quality of the overall uncertainty.
format Preprint
id arxiv_https___arxiv_org_abs_2505_15240
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Generalised Probabilistic Modelling and Improved Uncertainty Estimation in Comparative LLM-as-a-judge
Fathullah, Yassir
Gales, Mark J. F.
Artificial Intelligence
Machine Learning
This paper explores generalised probabilistic modelling and uncertainty estimation in comparative LLM-as-a-judge frameworks. We show that existing Product-of-Experts methods are specific cases of a broader framework, enabling diverse modelling options. Furthermore, we propose improved uncertainty estimates for individual comparisons, enabling more efficient selection and achieving strong performance with fewer evaluations. We also introduce a method for estimating overall ranking uncertainty. Finally, we demonstrate that combining absolute and comparative scoring improves performance. Experiments show that the specific expert model has a limited impact on final rankings but our proposed uncertainty estimates, especially the probability of reordering, significantly improve the efficiency of systems reducing the number of needed comparisons by ~50%. Furthermore, ranking-level uncertainty metrics can be used to identify low-performing predictions, where the nature of the probabilistic model has a notable impact on the quality of the overall uncertainty.
title Generalised Probabilistic Modelling and Improved Uncertainty Estimation in Comparative LLM-as-a-judge
topic Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2505.15240