Saved in:
Bibliographic Details
Main Authors: Rosales, Rafael, Miret, Santiago
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2507.21168
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916031351488512
author Rosales, Rafael
Miret, Santiago
author_facet Rosales, Rafael
Miret, Santiago
contents Effectively leveraging diversity has been shown to improve performance for various machine learning models, including large language models (LLMs). However, determining the most effective way of using diversity remains a challenge. In this work, we compare two diversity approaches for answering binary questions using LLMs: model diversity, which relies on multiple models answering the same question, and question interpretation diversity, which relies on using the same model to answer the same question framed in different ways. For both cases, we apply majority voting as the ensemble consensus heuristic to determine the final answer. Our experiments on boolq, strategyqa, and pubmedqa show that question interpretation diversity consistently leads to better ensemble accuracy compared to model diversity. Furthermore, our analysis of GPT and LLaMa shows that model diversity typically produces results between the best and the worst ensemble members without clear improvement.
format Preprint
id arxiv_https___arxiv_org_abs_2507_21168
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Diverse LLMs or Diverse Question Interpretations? That is the Ensembling Question
Rosales, Rafael
Miret, Santiago
Computation and Language
Artificial Intelligence
Machine Learning
68T50
I.2.7; I.2.0
Effectively leveraging diversity has been shown to improve performance for various machine learning models, including large language models (LLMs). However, determining the most effective way of using diversity remains a challenge. In this work, we compare two diversity approaches for answering binary questions using LLMs: model diversity, which relies on multiple models answering the same question, and question interpretation diversity, which relies on using the same model to answer the same question framed in different ways. For both cases, we apply majority voting as the ensemble consensus heuristic to determine the final answer. Our experiments on boolq, strategyqa, and pubmedqa show that question interpretation diversity consistently leads to better ensemble accuracy compared to model diversity. Furthermore, our analysis of GPT and LLaMa shows that model diversity typically produces results between the best and the worst ensemble members without clear improvement.
title Diverse LLMs or Diverse Question Interpretations? That is the Ensembling Question
topic Computation and Language
Artificial Intelligence
Machine Learning
68T50
I.2.7; I.2.0
url https://arxiv.org/abs/2507.21168