English
Related papers

Related papers: Calibration without Ground Truth

200 papers

Significant attention is being paid to multi-person pose estimation methods recently, as there has been rapid progress in the field owing to convolutional neural networks. Especially, recent method which exploits part confidence maps and…

Computer Vision and Pattern Recognition · Computer Science 2018-11-09 Naoki Kato , Tianqi Li , Kohei Nishino , Yusuke Uchida

Bilevel optimization, a hierarchical optimization paradigm, has gained significant attention in a wide range of practical applications, notably in the fine-tuning of generative models. However, due to the nested problem structure, most…

Optimization and Control · Mathematics 2025-07-29 Liuyuan Jiang , Quan Xiao , Lisha Chen , Tianyi Chen

Pretrained multilingual encoder models can directly perform zero-shot multilingual tasks or linguistic probing by reformulating the input examples into cloze-style prompts. This is accomplished by predicting the probabilities of the label…

Computation and Language · Computer Science 2023-10-20 Ercong Nie , Helmut Schmid , Hinrich Schütze

Verification of model outputs is rapidly emerging as a key primitive for both training and real-world deployment of large language models (LLMs). In practice, this often involves using imperfect LLM judges and reward models since ground…

Machine Learning · Statistics 2026-04-21 Joonhyuk Lee , Virginia Ma , Sarah Zhao , Yash Nair , Asher Spector , Regev Cohen , Emmanuel J. Candès

A reliable deep learning system should be able to accurately express its confidence with respect to its predictions, a quality known as calibration. One of the most effective ways to produce reliable confidence estimates with a pre-trained…

Machine Learning · Computer Science 2024-10-10 Thomas P. Zollo , Zhun Deng , Jake C. Snell , Toniann Pitassi , Richard Zemel

In today's AI-assisted software engineering landscape, developers increasingly depend on LLMs that are highly capable, yet inherently imperfect. The tendency of these models to produce incorrect outputs can reduce developer productivity. To…

Software Engineering · Computer Science 2026-04-09 Hong Yi Lin , Chunhua Liu , Haoyu Gao , Patanamon Thongtanunam , Christoph Treude

Semi-supervised learning has attracted significant attention due to the proliferation of applications featuring limited labeled data but abundant unlabeled data. In this paper, we examine the statistical inference problem in an…

Methodology · Statistics 2026-03-31 Chao Ying , Siyi Deng , Yang Ning , Jiwei Zhao , Heping Zhang

When deploying large language models (LLMs), it is important to ensure that these models are not only capable, but also reliable. Many benchmarks have been created to track LLMs' growing capabilities, however there has been no similar focus…

Machine Learning · Computer Science 2025-02-06 Joshua Vendrow , Edward Vendrow , Sara Beery , Aleksander Madry

Reinforcement Learning (RL) has been shown to substantially improve the reasoning capability of small and large language models (LLMs), but existing approaches typically rely on verifiable rewards, hence ground truth labels. We propose an…

Computation and Language · Computer Science 2026-04-06 Yiyang Shen , Lifu Tu , Weiran Wang

Aligning large language models (LLMs) with human values is a vital task for LLM practitioners. Current alignment techniques have several limitations: (1) requiring a large amount of annotated data; (2) demanding heavy human involvement; (3)…

Computation and Language · Computer Science 2024-01-17 Hongyi Guo , Yuanshun Yao , Wei Shen , Jiaheng Wei , Xiaoying Zhang , Zhaoran Wang , Yang Liu

Vision-language models (VLMs) have revolutionized machine learning by leveraging large pre-trained models to tackle various downstream tasks. Although label, training, and data efficiency have improved, many state-of-the-art VLMs still…

Computer Vision and Pattern Recognition · Computer Science 2025-03-03 Yushu Li , Yongyi Su , Adam Goodge , Kui Jia , Xun Xu

In the past decade, model-free reinforcement learning (RL) has provided solutions to challenging domains such as robotics. Model-based RL shows the prospect of being more sample-efficient than model-free methods in terms of…

Machine Learning · Computer Science 2021-04-14 John McLeod , Hrvoje Stojic , Vincent Adam , Dongho Kim , Jordi Grau-Moya , Peter Vrancx , Felix Leibfried

Recent advancements in large language models (LLMs) have led to their increased application across various tasks, with reinforcement learning from human feedback (RLHF) being a crucial part of their training to align responses with user…

Computation and Language · Computer Science 2024-10-29 Ben Hauptvogel , Malte Ostendorff , Georg Rehm , Sebastian Möller

Generalization is a central problem in Machine Learning. Indeed most prediction methods require careful calibration of hyperparameters usually carried out on a hold-out \textit{validation} dataset to achieve generalization. The main goal of…

Machine Learning · Statistics 2021-02-18 Karim Lounici , Katia Meziani , Benjamin Riu

Modern Large Language Models (LLMs) have shown rapid improvements in reasoning capabilities, driven largely by reinforcement learning (RL) with verifiable rewards. Here, we ask whether these LLMs can self-improve without the need for…

Computation and Language · Computer Science 2026-02-04 Yufan Zhuang , Chandan Singh , Liyuan Liu , Yelong Shen , Dinghuai Zhang , Jingbo Shang , Jianfeng Gao , Weizhu Chen

In contrast to the standard classification paradigm where the true class is given to each training pattern, complementary-label learning only uses training patterns each equipped with a complementary label, which only specifies one of the…

Machine Learning · Statistics 2019-11-20 Takashi Ishida , Gang Niu , Aditya Krishna Menon , Masashi Sugiyama

Recently there has been a surge of interest to deploy confidence set predictions rather than point predictions in machine learning. Unfortunately, the effectiveness of such prediction sets is frequently impaired by distribution shifts in…

Machine Learning · Computer Science 2025-08-14 Kevin Kasa , Zhiyu Zhang , Heng Yang , Graham W. Taylor

Language model (LM) post-training relies on two stages of human supervision: task demonstrations for supervised finetuning (SFT), followed by preference comparisons for reinforcement learning from human feedback (RLHF). As LMs become more…

Machine Learning · Computer Science 2025-01-15 Yaowen Ye , Cassidy Laidlaw , Jacob Steinhardt

The growing demand for large language models (LLMs) with tunable reasoning capabilities in many real-world applications highlights a critical need for methods that can efficiently produce a spectrum of models balancing reasoning depth and…

Artificial Intelligence · Computer Science 2025-09-30 Xiaochong Lan , Yu Zheng , Shiteng Cao , Yong Li

Calibration is a well-studied property of predictors which guarantees meaningful uncertainty estimates. Multicalibration is a related notion -- originating in algorithmic fairness -- which requires predictors to be simultaneously calibrated…

Machine Learning · Computer Science 2024-11-06 Dutch Hansen , Siddartha Devic , Preetum Nakkiran , Vatsal Sharan