paper-with-me

Papers

Confident Multiple Choice Learning

2017-06-12 · ICML 2017 8 · Kimin Lee, Changho Hwang, Kyoungsoo Park, Jinwoo Shin

Ensemble methods are arguably the most trustworthy techniques for boosting the performance of machine learning models. Popular independent ensembles (IE) relying on naive averaging/voting scheme have been of typical choice for most applications involving deep neural networks, but they do not consider advanced collaboration among ensemble models. In this paper, we propose new ensemble methods specialized for deep neural networks, called confident multiple choice learning (CMCL): it is a variant of multiple choice learning (MCL) via addressing its overconfidence issue.In particular, the proposed major components of CMCL beyond the original MCL scheme are (i) new loss, i.e., confident oracle loss, (ii) new architecture, i.e., feature sharing and (iii) new training method, i.e., stochastic labeling. We demonstrate the effect of CMCL via experiments on the image classification on CIFAR and SVHN, and the foreground-background segmentation on the iCoseg. In particular, CMCL using 5 residual networks provides 14.05% and 6.60% relative reductions in the top-1 error rates from the corresponding IE scheme for the classification task on CIFAR and SVHN, respectively.

📄 PDF Abstract BibTeX arXiv:1706.03475

Code (2)

chhwang/cmcl 공식 구현 tf
celsolbm/CMCL_Sequence pytorch

Tasks

General Classificationimage-classificationImage ClassificationMultiple-choice

Similar Papers 제목 키워드 기반

Answer Uncertainty and Unanswerability in Multiple-Choice Machine Reading Comprehension

2022-05-01 · Findings (ACL) 2022 5 · Vatsal Raina, Mark Gales

Machine reading comprehension (MRC) has drawn a lot of attention as an approach for assessing the ability of systems to understand natural language. Usually systems focus on selecting the correct answer to a question giv…

Machine Reading ComprehensionMultiple-choiceReading Comprehension

Answer Uncertainty and Unanswerability in Multiple-Choice Machine Reading Comprehension

2022-01-16 · ACL ARR January 2022 1 · Anonymous

Machine reading comprehension (MRC) has drawn a lot of attention as an approach for assessing the ability of systems to understand natural language. Usually systems focus on selecting the correct answer to a question giv…

Machine Reading ComprehensionMultiple-choiceReading Comprehension

Cautious Next Token Prediction

2025-07-03 · Yizhou Wang, Lingzhi Zhang, Yue Bai, Mang Tik Chiu 외

Next token prediction paradigm has been prevailing for autoregressive models in the era of LLMs. The current default sampling choice for popular LLMs is temperature scaling together with nucleus sampling to balance diver…

Prediction

Mind the Confidence Gap: Overconfidence, Calibration, and Distractor Effects in Large Language Models

2025-02-16 · Prateek Chhikara

Large Language Models (LLMs) demonstrate impressive performance across diverse tasks, yet confidence calibration remains a challenge. Miscalibration - where models are overconfident or underconfident - poses risks, parti…

Multiple-choice

Confident RAG: Enhancing the Performance of LLMs for Mathematics Question Answering through Multi-Embedding and Confidence Scoring

2025-07-23 · Shiting Chen, Zijian Zhao, Jinsong Chen arxiv

Large Language Models (LLMs) hold significant promise for mathematics education, yet they often struggle with complex mathematical reasoning. While Retrieval-Augmented Generation (RAG) mitigates these issues by grounding…

Mathematical ReasoningQuestion Answering