English
Related papers

Related papers: Calibration of Machine Reading Systems at Scale

200 papers

With the blooming of various Pre-trained Language Models (PLMs), Machine Reading Comprehension (MRC) has embraced significant improvements on various benchmarks and even surpass human performances. However, the existing works only target on…

Computation and Language · Computer Science 2020-11-16 Yiming Cui , Ting Liu , Shijin Wang , Guoping Hu

Large Language Models (LLMs) demonstrate remarkable performance in semantic understanding and generation, yet accurately assessing their output reliability remains a significant challenge. While numerous studies have explored calibration…

Artificial Intelligence · Computer Science 2024-12-18 Liangru Xie , Hui Liu , Jingying Zeng , Xianfeng Tang , Yan Han , Chen Luo , Jing Huang , Zhen Li , Suhang Wang , Qi He

Recent works have shown that language models (LM) capture different types of knowledge regarding facts or common sense. However, because no model is perfect, they still fail to provide appropriate answers in many cases. In this paper, we…

Computation and Language · Computer Science 2021-05-21 Zhengbao Jiang , Jun Araki , Haibo Ding , Graham Neubig

Accurately predicting the probabilities of user feedback, such as clicks and conversions, is critical for advertisement ranking and bidding. However, there often exist unwanted mismatches between predicted probabilities and true likelihoods…

Machine Learning · Computer Science 2024-05-22 Yuang Zhao , Chuhan Wu , Qinglin Jia , Hong Zhu , Jia Yan , Libin Zong , Linxuan Zhang , Zhenhua Dong , Muyu Zhang

Probabilistic predictions can be evaluated through comparisons with observed label frequencies, that is, through the lens of calibration. Recent scholarship on algorithmic fairness has started to look at a growing variety of…

Machine Learning · Computer Science 2023-05-16 Benedikt Höltgen , Robert C Williamson

In an increasing number of applications designers have access to multiple computer models which typically have different levels of fidelity and cost. Traditionally, designers calibrate these models one at a time against some high-fidelity…

Machine Learning · Computer Science 2025-06-02 Jonathan Tammer Eweis-Labolle , Tyler Johnson , Xiangyu Sun , Ramin Bostanabad

While in-context learning with large language models (LLMs) has shown impressive performance, we have discovered a unique miscalibration behavior where both correct and incorrect predictions are assigned the same level of confidence. We…

Computation and Language · Computer Science 2024-10-04 Wei Cheng , Tianlu Wang , Yanmin Ji , Fan Yang , Keren Tan , Yiyu Zheng

We consider the issue of calibration in large language models (LLM). Recent studies have found that common interventions such as instruction tuning often result in poorly calibrated LLMs. Although calibration is well-explored in traditional…

Machine Learning · Computer Science 2024-06-28 Maohao Shen , Subhro Das , Kristjan Greenewald , Prasanna Sattigeri , Gregory Wornell , Soumya Ghosh

Explaining and interpreting the decisions of recommender systems are becoming extremely relevant both, for improving predictive performance, and providing valid explanations to users. While most of the recent interest has focused on…

Information Retrieval · Computer Science 2019-06-19 Rishabh Jain , Pranava Madhyastha

Accurate uncertainty estimates are important in sequential model-based decision-making tasks such as Bayesian optimization. However, these estimates can be imperfect if the data violates assumptions made by the model (e.g., Gaussianity).…

Machine Learning · Computer Science 2024-06-27 Shachi Deshpande , Charles Marx , Volodymyr Kuleshov

Large language models optimized with techniques like RLHF have achieved good alignment in being helpful and harmless. However, post-alignment, these language models often exhibit overconfidence, where the expressed confidence does not…

Computation and Language · Computer Science 2024-10-10 Mozhi Zhang , Mianqiu Huang , Rundong Shi , Linsen Guo , Chong Peng , Peng Yan , Yaqian Zhou , Xipeng Qiu

Machine reading comprehension with unanswerable questions aims to abstain from answering when no answer can be inferred. In addition to extract answers, previous works usually predict an additional "no-answer" probability to detect…

Computation and Language · Computer Science 2018-11-16 Minghao Hu , Furu Wei , Yuxing Peng , Zhen Huang , Nan Yang , Dongsheng Li

Multimodal machine learning has achieved remarkable progress in a wide range of scenarios. However, the reliability of multimodal learning remains largely unexplored. In this paper, through extensive empirical studies, we identify current…

Machine Learning · Computer Science 2023-06-05 Huan Ma. Qingyang Zhang , Changqing Zhang , Bingzhe Wu , Huazhu Fu , Joey Tianyi Zhou , Qinghua Hu

A safe and trustworthy use of Large Language Models (LLMs) requires an accurate expression of confidence in their answers. We propose a novel Reinforcement Learning approach that allows to directly fine-tune LLMs to express calibrated…

Computation and Language · Computer Science 2026-03-03 David Bani-Harouni , Chantal Pellegrini , Paul Stangel , Ege Özsoy , Kamilia Zaripova , Nassir Navab , Matthias Keicher

The generalization performance of a risk prediction model can be evaluated by its calibration, which measures the agreement between predicted and observed outcomes on external validation data. Here, methods for assessing the calibration of…

Methodology · Statistics 2020-01-31 Moritz Berger , Matthias Schmid

Accurate quantification of uncertainty is crucial for real-world applications of machine learning. However, modern deep neural networks still produce unreliable predictive uncertainty, often yielding over-confident predictions. In this…

Machine Learning · Computer Science 2020-10-29 Peng Cui , Wenbo Hu , Jun Zhu

Reliable long-horizon value prediction is difficult in offline reinforcement learning because fitted value methods combine bootstrapping, function approximation, and distribution shift, while standard guarantees often require Bellman…

Machine Learning · Statistics 2026-05-11 Lars van der Laan , Nathan Kallus

Ensuring that classifiers are well-calibrated, i.e., their predictions align with observed frequencies, is a minimal and fundamental requirement for classifiers to be viewed as trustworthy. Existing methods for assessing multiclass…

Machine Learning · Computer Science 2025-10-30 Mahmoud Hegazy , Michael I. Jordan , Aymeric Dieuleveut

The Random Forest (RF) classifier is often claimed to be relatively well calibrated when compared with other machine learning methods. Moreover, the existing literature suggests that traditional calibration methods, such as isotonic…

Machine Learning · Computer Science 2025-01-29 Mohammad Hossein Shaker , Eyke Hüllermeier

Estimating the prevalence of a category in a population using imperfect measurement devices (diagnostic tests, classifiers, or large language models) is fundamental to science, public health, and online trust and safety. Standard approaches…

Artificial Intelligence · Computer Science 2026-04-24 Fridolin Linder , Thomas Leeper , Daniel Haimovich , Niek Tax , Lorenzo Perini , Milan Vojnovic