English
Related papers

Related papers: Joint Training for Selective Prediction

200 papers

Multi-task learning promises better model generalization on a target task by jointly optimizing it with an auxiliary task. However, the current practice requires additional labeling efforts for the auxiliary task, while not guaranteeing…

Computer Vision and Pattern Recognition · Computer Science 2022-10-14 Menelaos Kanakis , Thomas E. Huang , David Bruggemann , Fisher Yu , Luc Van Gool

We investigate a problem in which each member of a group of learners is trained separately to solve the same classification task. Each learner has access to a training dataset (possibly with overlap across learners) but each trained…

Machine Learning · Computer Science 2020-03-03 Mahmoud Albardan , John Klein , Olivier Colot

As LLMs are increasingly integrated into human-in-the-loop content moderation systems, a central challenge is deciding when their outputs can be trusted versus when escalation for human review is preferable. We propose a novel framework for…

Artificial Intelligence · Computer Science 2026-01-13 Or Bachar , Or Levi , Sardhendu Mishra , Adi Levi , Manpreet Singh Minhas , Justin Miller , Omer Ben-Porat , Eilon Sheetrit , Jonathan Morra

Machine learning techniques are used to predict theoretical constraints such as unitarity and boundedness from below in extensions of the Standard Model. This approach has proven effective for models incorporating additional SU(2) scalar…

High Energy Physics - Phenomenology · Physics 2025-12-19 Darius Jurčiukonis

The next-token prediction (NTP) objective trains language models to predict a single token at each step, even though many continuations can express the same meaning. For example, in the sentence ``this sticker can be placed here'',…

Computation and Language · Computer Science 2026-05-26 Christine Zhang , Dan Jurafsky , Chen Shani

Classification is one of the most important tasks in Machine Learning (ML) and with recent advancements in artificial intelligence (AI) it is important to find efficient ways to implement it. Generally, the choice of classification…

Machine Learning · Computer Science 2023-12-27 Anuja Dixit , Shreya Byreddy , Guanqun Song , Ting Zhu

Scheduled sampling is an effective method to alleviate the exposure bias problem of neural machine translation. It simulates the inference scene by randomly replacing ground-truth target input tokens with predicted ones during training.…

Computation and Language · Computer Science 2021-07-23 Yijin Liu , Fandong Meng , Yufeng Chen , Jinan Xu , Jie Zhou

Learning efficient representations for decision-making policies is a challenge in imitation learning (IL). Current IL methods require expert demonstrations, which are expensive to collect. Additionally, they are not explicitly trained to…

Machine Learning · Computer Science 2026-03-19 Aleksandar Vujinovic , Aleksandar Kovacevic

While supervised learning models have shown remarkable performance in various natural language processing (NLP) tasks, their success heavily relies on the availability of large-scale labeled datasets, which can be costly and time-consuming…

Computation and Language · Computer Science 2024-06-04 Wrick Talukdar , Anjanava Biswas

Multi-modal learning focuses on training models by equally combining multiple input data modalities during the prediction process. However, this equal combination can be detrimental to the prediction accuracy because different modalities…

Computer Vision and Pattern Recognition · Computer Science 2022-07-25 Hu Wang , Jianpeng Zhang , Yuanhong Chen , Congbo Ma , Jodie Avery , Louise Hull , Gustavo Carneiro

An increasingly common setting in machine learning involves multiple parties, each with their own data, who want to jointly make predictions on future test points. Agents wish to benefit from the collective expertise of the full set of…

Machine Learning · Computer Science 2021-06-24 Celestine Mendler-Dünner , Wenshuo Guo , Stephen Bates , Michael I. Jordan

Large language models such as GPT and Llama are trained with a next-token prediction loss. In this work, we suggest that training language models to predict multiple future tokens at once results in higher sample efficiency. More…

Computation and Language · Computer Science 2024-05-01 Fabian Gloeckle , Badr Youbi Idrissi , Baptiste Rozière , David Lopez-Paz , Gabriel Synnaeve

Using the bit string generation problem as a case study, we theoretically compare two standard methods for adapting large language models to new tasks. The first, referred to as supervised fine-tuning, involves training a new next token…

Machine Learning · Statistics 2026-03-31 Seamus Somerstep , Vinod Raman , Unique Subedi , Yuekai Sun

Scheduled sampling is widely used to mitigate the exposure bias problem for neural machine translation. Its core motivation is to simulate the inference scene during training by replacing ground-truth tokens with predicted tokens, thus…

Computation and Language · Computer Science 2021-09-01 Yijin Liu , Fandong Meng , Yufeng Chen , Jinan Xu , Jie Zhou

The goal of continual learning is to improve the performance of recognition models in learning sequentially arrived data. Although most existing works are established on the premise of learning from scratch, growing efforts have been…

Computer Vision and Pattern Recognition · Computer Science 2023-10-10 Gengwei Zhang , Liyuan Wang , Guoliang Kang , Ling Chen , Yunchao Wei

Spoken language recognition (SLR) refers to the automatic process used to determine the language present in a speech sample. SLR is an important task in its own right, for example, as a tool to analyze or categorize large amounts of…

Computation and Language · Computer Science 2022-08-15 Luciana Ferrer , Diego Castan , Mitchell McLaren , Aaron Lawson

Large language models such as GPT and Llama are trained with a next-token prediction loss. In this work, we suggest that training language models to predict multiple future tokens at once results in higher sample efficiency. More…

Computation and Language · Computer Science 2026-03-03 Athul Radhakrishnan , Siddhant Mohan , Mahima Sachdeva

Supervised distributional methods are applied successfully in lexical entailment, but recent work questioned whether these methods actually learn a relation between two words. Specifically, Levy et al. (2015) claimed that linear classifiers…

Computation and Language · Computer Science 2018-04-25 Tu Vu , Vered Shwartz

The performance of Large Language Models (LLMs) relies heavily on the quality of prompts, which are often manually engineered and task-specific, making them costly and non-scalable. We propose a novel approach, Supervisory Prompt Training…

Computation and Language · Computer Science 2024-03-28 Jean Ghislain Billa , Min Oh , Liang Du

We propose a novel and simple method for semi-supervised text classification. The method stems from the hypothesis that a classifier with pretrained word embeddings always outperforms the same classifier with randomly initialized word…

Computation and Language · Computer Science 2019-10-01 Hwiyeol Jo , Ceyda Cinarel