English
Related papers

Related papers: Great Models Think Alike: Improving Model Reliabil…

200 papers

In large deep neural networks that seem to perform surprisingly well on many tasks, we also observe a few failures related to accuracy, social biases, and alignment with human values, among others. Therefore, before deploying these models,…

Machine Learning · Computer Science 2024-06-17 Som Sagar , Aditya Taparia , Ransalu Senanayake

Time-series forecasting models often encounter abrupt changes in a given period of time which generally occur due to unexpected or unknown events. Despite their scarce occurrences in the training set, abrupt changes incur loss that…

Machine Learning · Computer Science 2023-09-25 Junwoo Park , Jungsoo Lee , Youngin Cho , Woncheol Shin , Dongmin Kim , Jaegul Choo , Edward Choi

With the growing adoption of deep learning models in different real-world domains, including computational biology, it is often necessary to understand which data features are essential for the model's decision. Despite extensive recent…

Machine Learning · Computer Science 2022-10-04 Prashnna K Gyawali , Xiaoxia Liu , James Zou , Zihuai He

Models play an essential role in the design process of cyber-physical systems. They form the basis for simulation and analysis and help in identifying design problems as early as possible. However, the construction of models that comprise…

With model trustworthiness being crucial for sensitive real-world applications, practitioners are putting more and more focus on improving the uncertainty calibration of deep neural networks. Calibration errors are designed to quantify the…

Machine Learning · Computer Science 2024-03-14 Sebastian G. Gruber , Florian Buettner

Benchmarks underpin how progress in large language models (LLMs) is measured and trusted. Yet our analyses reveal that apparent convergence in benchmark accuracy can conceal deep epistemic divergence. Using two major reasoning benchmarks -…

Computation and Language · Computer Science 2026-02-13 Eddie Yang , Dashun Wang

In machine learning, accurately predicting the probability that a specific input is correct is crucial for risk management. This process, known as uncertainty (or confidence) estimation, is particularly important in mission-critical…

Machine Learning · Computer Science 2023-01-12 Gabriella Chouraqui , Liron Cohen , Gil Einziger , Liel Leman

To achieve high performance of a machine learning (ML) task, a deep learning-based model must implicitly capture the entire distribution from data. Thus, it requires a huge amount of training samples, and data are expected to fully present…

Machine Learning · Computer Science 2021-11-17 Hung Nguyen , Morris Chang

Aligning large language models (LLMs) with human preferences is crucial for enhancing their utility in terms of helpfulness, truthfulness, safety, harmlessness, and interestingness. Existing methods for achieving this alignment often…

Computation and Language · Computer Science 2024-07-04 Wenhao Liu , Xiaohua Wang , Muling Wu , Tianlong Li , Changze Lv , Zixuan Ling , Jianhao Zhu , Cenyuan Zhang , Xiaoqing Zheng , Xuanjing Huang

We propose a method for jointly inferring labels across a collection of data samples, where each sample consists of an observation and a prior belief about the label. By implicitly assuming the existence of a generative model for which a…

Machine Learning · Computer Science 2022-06-22 Esther Rolf , Nikolay Malkin , Alexandros Graikos , Ana Jojic , Caleb Robinson , Nebojsa Jojic

The emergence of Large Language Models (LLMs) has revealed a growing need for human-AI collaboration, especially in creative decision-making scenarios where trust and reliance are paramount. Through human studies and model evaluations on…

Computation and Language · Computer Science 2024-10-07 Manasi Sharma , Ho Chit Siu , Rohan Paleja , Jaime D. Peña

Reinforcement learning from human feedback (RLHF) is widely used to train large language models (LLMs). However, it is unclear whether LLMs accurately learn the underlying preferences in human feedback data. We coin the term \textit{Learned…

Machine Learning · Computer Science 2025-09-22 Luke Marks , Amir Abdullah , Clement Neo , Rauno Arike , David Krueger , Philip Torr , Fazl Barez

Large language models (LLMs) power many state-of-the-art systems in natural language processing. However, these models are extremely computationally expensive, even at inference time, raising the natural question: when is the extra cost of…

Machine Learning · Computer Science 2023-05-05 Deepak Narayanan , Keshav Santhanam , Peter Henderson , Rishi Bommasani , Tony Lee , Percy Liang

Learning an effective global model on private and decentralized datasets has become an increasingly important challenge of machine learning when applied in practice. Existing distributed learning paradigms, such as Federated Learning,…

Machine Learning · Computer Science 2023-06-05 Tengfei Ma , Trong Nghia Hoang , Jie Chen

Fine-tuning LLMs on tabular classification tasks can lead to the phenomenon of fine-tuning multiplicity where equally well-performing models make conflicting predictions on the same input. Fine-tuning multiplicity can arise due to…

Machine Learning · Computer Science 2025-06-05 Faisal Hamman , Pasan Dissanayake , Saumitra Mishra , Freddy Lecue , Sanghamitra Dutta

Large Language Models (LLMs) have gained significant popularity in recent years for their ability to answer questions in various fields. However, these models have a tendency to "hallucinate" their responses, making it challenging to…

Computation and Language · Computer Science 2024-11-25 Elizaveta Reganova , Peter Steinbach

Although pretrained language models (PTLMs) have been shown to contain significant amounts of world knowledge, they can still produce inconsistent answers to questions when probed, even after using specialized training techniques to reduce…

Computation and Language · Computer Science 2021-10-08 Nora Kassner , Oyvind Tafjord , Hinrich Schutze , Peter Clark

Model editing techniques are essential for efficiently updating knowledge in large language models (LLMs). However, the effectiveness of existing approaches degrades in massive editing scenarios, particularly when evaluated with practical…

Computation and Language · Computer Science 2026-02-25 Yanbo Dai , Zhenlan Ji , Zongjie Li , Shuai Wang

Deep learning models frequently make incorrect predictions with high confidence when presented with test examples that are not well represented in their training dataset. We propose a novel and straightforward approach to estimate…

Machine Learning · Computer Science 2019-10-04 Tiago Ramalho , Miguel Miranda

The condition of parameter identifiability is essential for the consistency of all estimators and is often challenging to prove. As a consequence, this condition is often assumed for simplicity although this may not be straightforward to…

Statistics Theory · Mathematics 2016-07-21 Stéphane Guerrier , Roberto Molinari