English
Related papers

Related papers: Towards Improving Selective Prediction Ability of …

200 papers

The advent of pre-trained language models (PLMs) has enabled significant performance gains in the field of natural language processing. However, recent studies have found PLMs to suffer from miscalibration, indicating a lack of accuracy in…

Computation and Language · Computer Science 2024-12-23 Geetanjali Bihani , Julia Rayz

Bayesian inference allows expressing the uncertainty of posterior belief under a probabilistic model given prior information and the likelihood of the evidence. Predominantly, the likelihood function is only implicitly established by a…

The field of algorithms with predictions incorporates machine learning advice in the design of online algorithms to improve real-world performance. A central consideration is the extent to which predictions can be trusted -- while existing…

Machine Learning · Statistics 2026-03-26 Judy Hanwen Shen , Ellen Vitercik , Anders Wikum

Handling uncertainty is critical for ensuring reliable decision-making in intelligent systems. Modern neural networks are known to be poorly calibrated, resulting in predicted confidence scores that are difficult to use. This article…

Machine Learning · Computer Science 2026-05-18 Gabriele Sanguin , Arjun Pakrashi , Marco Viola , Francesco Rinaldi

Since deep learning became a key player in natural language processing (NLP), many deep learning models have been showing remarkable performances in a variety of NLP tasks, and in some cases, they are even outperforming humans. Such high…

Computation and Language · Computer Science 2019-08-07 Sangchul Hahn , Heeyoul Choi

Generating calibrated and sharp neural network predictive distributions for regression problems is essential for optimal decision-making in many real-world applications. To address the miscalibration issue of neural networks, various…

Machine Learning · Computer Science 2024-03-19 Victor Dheur , Souhaib Ben Taieb

Humans work together to solve common problems by having discussions, explaining, and agreeing or disagreeing with each other. Similarly, if a system can have discussions with humans when solving tasks, it can improve the system's…

Computation and Language · Computer Science 2024-01-31 Masahiro Kaneko , Graham Neubig , Naoaki Okazaki

Many natural language processing (NLP) tasks involve subjectivity, ambiguity, or legitimate disagreement between annotators. In this paper, we outline our system for modeling human variation. Our system leverages language models' (LLMs)…

Computation and Language · Computer Science 2025-10-09 Taylor Sorensen , Yejin Choi

Large-scale pre-trained models have achieved remarkable success in many applications, but how to leverage them to improve the prediction reliability of downstream models is undesirably under-explored. Moreover, modern neural networks have…

Machine Learning · Computer Science 2023-10-31 Peng Cui , Dan Zhang , Zhijie Deng , Yinpeng Dong , Jun Zhu

With the increasing deployment of machine learning models in many socially sensitive tasks, there is a growing demand for reliable and trustworthy predictions. One way to accomplish these requirements is to allow a model to abstain from…

Machine Learning · Computer Science 2024-09-19 Andrea Pugnana , Lorenzo Perini , Jesse Davis , Salvatore Ruggieri

Modern NLP systems require high-quality annotated data. In specialized domains, expert annotations may be prohibitively expensive. An alternative is to rely on crowdsourcing to reduce costs at the risk of introducing noise. In this paper we…

Computation and Language · Computer Science 2019-05-21 Yinfei Yang , Oshin Agarwal , Chris Tar , Byron C. Wallace , Ani Nenkova

The wide-spread adoption of representation learning technologies in clinical decision making strongly emphasizes the need for characterizing model reliability and enabling rigorous introspection of model behavior. While the former need is…

Machine Learning · Computer Science 2020-05-01 Jayaraman J. Thiagarajan , Prasanna Sattigeri , Deepta Rajan , Bindya Venkatesh

Machine learning algorithms typically assume that training and test examples are drawn from the same distribution. However, distribution shift is a common problem in real-world applications and can cause models to perform dramatically worse…

Machine Learning · Computer Science 2022-06-22 Huaxiu Yao , Yu Wang , Sai Li , Linjun Zhang , Weixin Liang , James Zou , Chelsea Finn

Selective prediction [Dru13, QV19] models the scenario where a forecaster freely decides on the prediction window that their forecast spans. Many data statistics can be predicted to a non-trivial error rate without any distributional…

Machine Learning · Computer Science 2025-08-14 Licheng Liu , Mingda Qiao

Natural Language Inference (NLI) models are known to learn from biases and artefacts within their training data, impacting how well they generalise to other unseen datasets. Existing de-biasing approaches focus on preventing the models from…

Computation and Language · Computer Science 2022-05-03 Joe Stacey , Yonatan Belinkov , Marek Rei

Reinforcement learning (RL) has proven remarkably effective at improving the accuracy of language models in verifiable and deterministic domains like mathematics. Here, we examine if current RL methods are also effective at optimizing…

Machine Learning · Computer Science 2025-08-19 Michael Bereket , Jure Leskovec

Quantification of Uncertainty in predictions is a challenging problem. In the classification settings, although deep learning based models generalize well, class probabilities often lack reliability. Calibration errors are used to quantify…

Machine Learning · Computer Science 2024-05-07 Aditya Challa , Snehanshu Saha , Soma Dhavala

The emergence of in-context learning (ICL) enables large pre-trained language models (PLMs) to make predictions for unseen inputs without updating parameters. Despite its potential, ICL's effectiveness heavily relies on the quality,…

Machine Learning · Computer Science 2024-07-02 Xiaoling Zhou , Wei Ye , Yidong Wang , Chaoya Jiang , Zhemg Lee , Rui Xie , Shikun Zhang

Training a model with access to human explanations can improve data efficiency and model performance on in- and out-of-domain data. Adding to these empirical findings, similarity with the process of human learning makes learning from…

Computation and Language · Computer Science 2022-04-20 Mareike Hartmann , Daniel Sonntag

Large language models (LLMs) are increasingly used in statistical research and applications. However,they are also notorious for unreliable or biased information. Here, we explore whether LLMs can be used to improve the precision of…

Applications · Statistics 2026-05-29 Jaylin Lowe , Adam Sales , Johann A. Gagnon-Bartsch