Despite huge advances, LLMs still lack convenient and reliable methods to quantify the uncertainty in their responses, making them difficult to trust in high-stakes applications. One of the simplest approaches to eliciting more accurate answers is to select the mode of many responses, a technique known as ensembling. In this work, we expand on typical ensembling approaches by looking at ensembles with a variable voting threshold. We introduce a theoretical framework for question answering and show that, by permitting ensembles to "abstain" from providing an answer when the dominant response falls short of the threshold, it is possible to dramatically increase the trustworthiness of the remaining answers. From this framework, we derive theoretical results as well as report experimental results on two problem domains: arithmetic problem solving and clinical-note question-answering. In both domains, we observe that large gains in answer trustworthiness can be achieved using highly restrictive voting ensembles, while incurring relatively modest reductions in response yield and accuracy. Due to this quality, voting ensembles may be particularly useful in applications - such as healthcare and data annotation - that require a high degree of certainty but which may not require that every question receive an automated answer.
TRUSTVIS: A Multi-Dimensional Trustworthiness Evaluation Framework for Large Language Models
University of Alberta（阿尔伯塔大学）；Mila - Quebec Artificial Intelligence Institute（魁北克人工智能研究所）；The University of Tokyo（东京大学）；Macau University of Science and Technology（澳门科学技术大学）
From Pixels to Explanations: Interpretable Diabetic Retinopathy Grading with CNN-Transformer Ensembles, Visual Explainability and Vision-Language Models
Department of Informatics, University of Salerno（萨勒诺大学信息学院）；Department of Information Security and Communication Technology (IIK), Norwegian University of Science and Technology（挪威科技大学信息安全部）
SpecFuse: Ensembling Large Language Models via Next-Segment Prediction
Peng Cheng Laboratory（鹏城实验室）；Key Lab of Intelligent Information Processing, Institute of Computing Technology, Chinese Academy of Sciences (ICT/CAS)（中国科学院计算技术研究所智能信息处理重点实验室）；University of Chinese Academy of Sciences（中国科学院大学）；Tianjin Laboratory Autonomous Intelligence Technology and Systems, School of Computer Science and Technology, Tiangong University（天津工业大学计算机科学与技术学院天津市自主智能技术与系统实验室）；Institute for Advanced Algorithms Research, Shanghai（上海高级算法研究所）
OntoAligner-Ensemble: Voting-Based Fusion across Heterogeneous Ontology Alignment Techniques
TIB Leibniz Information Centre for Science and Technology（莱布尼茨科学与技术信息中心）；L3S Research Center, Leibniz University of Hannover（汉诺威莱布尼茨大学L3S研究中心）；Graphwise；University of Tabriz（大不里士大学）
An Intelligent Decision Support Ensemble Voting Model for Coronary Artery Disease Prediction in Smart Healthcare Monitoring Environments
LASTIMI, High School of Technology Mohammed V University in Rabat Sale, Morocco；LASTIMI, Mohammedia School of Engineers Mohammed V University in Rabat Rabat, Morocco；CISIEV. Faculty of Science；Technology in Marrakech Cadi Ayyad University Marrakech, Morocco
Object Classification Model Using Ensemble Learning with Gray-Level Co-Occurrence Matrix and Histogram Extraction
Faculty of Information Technology Universitas Kristen Satya Wacana（Satya Wacana 基督教大学信息技术学院）；Institut Teknologi dan Bisnis STIKOM Bali（巴厘 STIKOM 科技与商业学院）
Multi Loss-based Feature Fusion and Top Two Voting Ensemble Decision Strategy for Facial Expression Recognition in the Wild
School of Computer and Artificial Intelligence, Southwest Jiaotong University（西南交通大学计算机与人工智能学院）；Chengdu University（成都大学）；China National Offshore Oil Corporation（中国海洋石油集团有限公司）；School of Information and Software Engineering, University of Electronic Science and Technology of China（电子科技大学信息与软件工程学院）
