paper-with-me

Papers

Improving Confidence Estimates for Unfamiliar Examples

2018-04-09 · CVPR 2020 6 · Zhizhong Li, Derek Hoiem

Intuitively, unfamiliarity should lead to lack of confidence. In reality, current algorithms often make highly confident yet wrong predictions when faced with relevant but unfamiliar examples. A classifier we trained to recognize gender is 12 times more likely to be wrong with a 99% confident prediction if presented with a subject from a different age group than those seen during training. In this paper, we compare and evaluate several methods to improve confidence estimates for unfamiliar and familiar samples. We propose a testing methodology of splitting unfamiliar and familiar samples by attribute (age, breed, subcategory) or sampling (similar datasets collected by different people at different times). We evaluate methods including confidence calibration, ensembles, distillation, and a Bayesian model and use several metrics to analyze label, likelihood, and calibration error. While all methods reduce over-confident errors, the ensemble of calibrated models performs best overall, and T-scaling performs best among the approaches with fastest inference. Our code is available at https://github.com/lizhitwo/ConfidenceEstimates . $\color{red}{\text{Please see UPDATED ERRATA.}}$

📄 PDF Abstract BibTeX arXiv:1804.03166

Code (1)

lizhitwo/ConfidenceEstimates 공식 구현 pytorch

Tasks

AttributeDomain Adaptation

Similar Papers 제목 키워드 기반

Unfamiliar Finetuning Examples Control How Language Models Hallucinate

2024-03-08 · Katie Kang, Eric Wallace, Claire Tomlin, Aviral Kumar 외

Large language models are known to hallucinate when faced with unfamiliar queries, but the underlying mechanism that govern how models hallucinate are not yet fully understood. In this work, we find that unfamiliar examp…

MMLUMultiple-choiceTriviaQA

Conversational Artificial Intelligence in Natural Language Processing Application with Lifelong Learning

2021-09-29 · Ade Oktavianus Kurniawan, Kevin Natio Banjarnahor

Conversational AI bot known as chatbot has many roles in human life today, such as answering uncomplicated questions on E-commerce website pages or even help as an assistant like Siri and Google assistant. However, the c…

ChatbotLifelong learning

Your Pre-trained LLM is Secretly an Unsupervised Confidence Calibrator

2025-05-22 · Beier Luo, Shuoyuan Wang, Yixuan Li, Hongxin Wei

Post-training of large language models is essential for adapting pre-trained language models (PLMs) to align with human preferences and downstream tasks. While PLMs typically exhibit well-calibrated confidence, post-trai…

Learning Confidence for Out-of-Distribution Detection in Neural Networks

2018-02-13 · Terrance DeVries, Graham W. Taylor

Modern neural networks are very powerful predictive models, but they are often incapable of recognizing when their predictions may be wrong. Closely related to this is the task of out-of-distribution detection, where a n…

Out-of-Distribution Detection

Few-Shot Recalibration of Language Models

2024-03-27 · Xiang Lisa Li, Urvashi Khandelwal, Kelvin Guu

Recent work has uncovered promising ways to extract well-calibrated confidence estimates from language models (LMs), where the model's confidence score reflects how likely it is to be correct. However, while LMs may appe…

MathMMLU