English
Related papers

Related papers: Model Agreement via Anchoring

200 papers

Model selection is a problem that has occupied machine learning researchers for a long time. Recently, its importance has become evident through applications in deep learning. We propose an agreement-based learning framework that prevents…

Machine Learning · Computer Science 2018-06-05 Emmanouil Antonios Platanios

As various post hoc explanation methods are increasingly being leveraged to explain complex models in high-stakes settings, it becomes critical to develop a deeper understanding of whether and when the explanations output by these methods…

Machine Learning · Computer Science 2025-04-18 Satyapriya Krishna , Tessa Han , Alex Gu , Steven Wu , Shahin Jabbari , Himabindu Lakkaraju

Modern language models often exhibit powerful but brittle behavior, leading to the development of larger and more diverse benchmarks to reliably assess their behavior. Here, we suggest that model performance can be benchmarked and…

Computation and Language · Computer Science 2024-02-20 Rajan Vivek , Kawin Ethayarajh , Diyi Yang , Douwe Kiela

Detecting when a language model is wrong without ground truth labels is a fundamental challenge for safe deployment. Existing approaches rely on a model's own uncertainty -- such as token entropy or confidence scores -- but these signals…

Artificial Intelligence · Computer Science 2026-03-27 Matt Gorbett , Suman Jana

Anchoring is a recent, architecture-agnostic principle for training deep neural networks that has been shown to significantly improve uncertainty estimation, calibration, and extrapolation capabilities. In this paper, we systematically…

Machine Learning · Computer Science 2024-06-04 Vivek Narayanaswamy , Kowshik Thopalli , Rushil Anirudh , Yamen Mubarka , Wesam Sakla , Jayaraman J. Thiagarajan

Evaluating the performance of machine learning models under distribution shift is challenging, especially when we only have unlabeled data from the shifted (target) domain, along with labeled data from the original (source) domain. Recent…

Machine Learning · Statistics 2023-03-02 Donghwan Lee , Behrad Moniri , Xinmeng Huang , Edgar Dobriban , Hamed Hassani

While interpretability methods identify a model's learned concepts, they overlook the relationships between concepts that make up its abstractions and inform its ability to generalize to new data. To assess whether models' have learned…

Machine Learning · Computer Science 2025-11-04 Angie Boggust , Hyemin Bang , Hendrik Strobelt , Arvind Satyanarayan

Machine learning (ML) models have been quite successful in predicting outcomes in many applications. However, in some cases, domain experts might have a judgment about the expected outcome that might conflict with the prediction of ML…

Machine Learning · Computer Science 2023-05-02 Hogun Park , Aly Megahed , Peifeng Yin , Yuya Ong , Pravar Mahajan , Pei Guo

The deployment of pre-trained perception models in novel environments often leads to performance degradation due to distributional shifts. Although recent artificial intelligence approaches for metacognition use logical rules to…

Machine unlearning, an emerging research topic focusing on compliance with data privacy regulations, enables trained models to remove the information learned from specific data. While many existing methods indirectly address this issue by…

Machine Learning · Computer Science 2024-12-24 Seonguk Seo , Dongwan Kim , Bohyung Han

Reasoning models frequently agree with incorrect user suggestions -- a behavior known as sycophancy. However, it is unclear where in the reasoning trace this agreement originates and how strong the commitment is. We introduce…

Artificial Intelligence · Computer Science 2026-02-10 Jacek Duszenko

Disagreement-based approaches generate multiple classifiers and exploit the disagreement among them with unlabeled data to improve learning performance. Co-training is a representative paradigm of them, which trains two classifiers…

Machine Learning · Computer Science 2017-08-16 Wei Wang , Zhi-Hua Zhou

A single informed agent can draw an arbitrarily large network to the ground truth. This is the sharpest consequence of the "Averaging plus Learning" framework studied here, where agents update opinions by socially averaging neighbours while…

Dynamical Systems · Mathematics 2026-03-03 Ionel Popescu , Jeven Syatriadi , Tushar Vaidya

While explainability is a desirable characteristic of increasingly complex black-box models, modern explanation methods have been shown to be inconsistent and contradictory. The semantics of explanations is not always fully understood - to…

Artificial Intelligence · Computer Science 2024-08-09 Omer Reingold , Judy Hanwen Shen , Aditi Talati

Model multiplicity refers to the existence of multiple machine learning models that describe the data equally well but may produce different predictions on individual samples. In medicine, these models can admit conflicting predictions for…

Model update is a crucial process in the operation of ML/AI systems. While updating a model generally enhances the average prediction performance, it also significantly impacts the explanations of predictions. In real-world applications,…

Machine Learning · Computer Science 2024-08-06 Ryuta Matsuno

While neural models show remarkable accuracy on individual predictions, their internal beliefs can be inconsistent across examples. In this paper, we formalize such inconsistency as a generalization of prediction error. We propose a…

Artificial Intelligence · Computer Science 2019-09-16 Tao Li , Vivek Gupta , Maitrey Mehta , Vivek Srikumar

Current alignment evaluation mostly measures whether models encode dangerous concepts and whether they refuse harmful requests. Both miss the layer where alignment often operates: routing from concept detection to behavioral policy. We…

Machine Learning · Computer Science 2026-05-04 Gregory N. Frank

Zero-Shot Super-Resolution Spatiotemporal Forecasting requires a deep learning model to be trained on low-resolution data and deployed for inference on high-resolution. Existing studies consider maintaining similar error across different…

Computer Vision and Pattern Recognition · Computer Science 2026-02-10 Wenshuo Wang , Fan Zhang

Recent work has shown that models trained to the same objective, and which achieve similar measures of accuracy on consistent test data, may nonetheless behave very differently on individual predictions. This inconsistency is undesirable in…

Machine Learning · Computer Science 2021-11-17 Emily Black , Klas Leino , Matt Fredrikson
‹ Prev 1 2 3 10 Next ›