English
Related papers

Related papers: Selective Weak-to-Strong Generalization

200 papers

Weak-to-strong generalization refers to the phenomenon where a stronger model trained under supervision from a weaker one can outperform its teacher. While prior studies aim to explain this effect, most theoretical insights are limited to…

Machine Learning · Computer Science 2025-10-30 Junsoo Oh , Jerry Song , Chulhee Yun

Standard techniques for aligning large language models (LLMs) utilize human-produced data, which could limit the capability of any aligned LLM to human level. Label refinement and weak training have emerged as promising strategies to…

Machine Learning · Statistics 2025-08-26 Seamus Somerstep , Ya'acov Ritov , Mikhail Yurochkin , Subha Maity , Yuekai Sun

Weak supervision (WS) is a rich set of techniques that produce pseudolabels by aggregating easily obtained but potentially noisy label estimates from a variety of sources. WS is theoretically well understood for binary classification, where…

Machine Learning · Computer Science 2022-11-28 Harit Vishwakarma , Nicholas Roberts , Frederic Sala

Curation of large fully supervised datasets has become one of the major roadblocks for machine learning. Weak supervision provides an alternative to supervised learning by training with cheap, noisy, and possibly correlated labeling…

Machine Learning · Computer Science 2021-06-01 Chidubem Arachie , Bert Huang

Neural ranking models (NRMs) have demonstrated effective performance in several information retrieval (IR) tasks. However, training NRMs often requires large-scale training data, which is difficult and expensive to obtain. To address this…

Information Retrieval · Computer Science 2023-04-19 Yen-Chieh Lien , Hamed Zamani , W. Bruce Croft

Weak-to-strong generalization (W2SG) refers to the phenomenon where a strong student model, trained on a dataset labeled by a weak teacher, ultimately outperforms the teacher on the target task. Recent studies attribute this performance…

Machine Learning · Computer Science 2025-09-30 Gengze Xu , Wei Yao , Ziqiao Wang , Yong Liu

Superalignment, where humans act as weak supervisors for superhuman models, has become a crucial problem with the rapid development of Large Language Models (LLMs). Recent work has preliminarily studied this problem by using weak models to…

Computation and Language · Computer Science 2025-03-03 Wenkai Yang , Shiqi Shen , Guangyao Shen , Wei Yao , Yong Liu , Zhi Gong , Yankai Lin , Ji-Rong Wen

As future superhuman models become increasingly complex, accurately supervising their behavior may exceed human capabilities. Recent works have demonstrated that in such scenarios, weak models can effectively supervise strong models, a…

Machine Learning · Computer Science 2025-11-27 Myeongho Jeon , Jan Sobotka , Suhwan Choi , Maria Brbić

Strong student models can learn from weaker teachers: when trained on the predictions of a weaker model, a strong pretrained student can learn to correct the weak model's errors and generalize to examples where the teacher is not confident,…

Machine Learning · Computer Science 2024-05-28 Hunter Lang , David Sontag , Aravindan Vijayaraghavan

In many applications, training machine learning models involves using large amounts of human-annotated data. Obtaining precise labels for the data is expensive. Instead, training with weak supervision provides a low-cost alternative. We…

Machine Learning · Computer Science 2022-02-09 Chidubem Arachie , Bert Huang

Modern large language model (LLM) alignment techniques rely on human feedback, but it is unclear whether these techniques fundamentally limit the capabilities of aligned LLMs. In particular, it is unknown if it is possible to align…

In scientific reasoning tasks, the veracity of the reasoning process is as critical as the final outcome. While Process Reward Models (PRMs) offer a solution to the coarse-grained supervision problems inherent in Outcome Reward Models…

Computation and Language · Computer Science 2026-03-10 Chi-Min Chan , Ehsan Hajiramezanali , Xiner Li , Edward De Brouwer , Carl Edwards , Wei Xue , Sirui Han , Yike Guo , Gabriele Scalia

As large language models advance toward superhuman performance, ensuring their alignment with human values and abilities grows increasingly complex. Weak-to-strong generalization offers a promising approach by leveraging predictions from…

Machine Learning · Computer Science 2025-05-29 Wei Yao , Wenkai Yang , Ziqiao Wang , Yankai Lin , Yong Liu

In this paper, we propose a method for training neural networks when we have a large set of data with weak labels and a small amount of data with true labels. In our proposed model, we train two neural networks: a target network, the…

Machine Learning · Statistics 2017-12-01 Mostafa Dehghani , Aliaksei Severyn , Sascha Rothe , Jaap Kamps

Existing weak supervision approaches use all the data covered by weak signals to train a classifier. We show both theoretically and empirically that this is not always optimal. Intuitively, there is a tradeoff between the amount of…

Machine Learning · Statistics 2023-03-08 Hunter Lang , Aravindan Vijayaraghavan , David Sontag

Steering the behavior of a strong model pre-trained on internet-scale data can be difficult due to the scarcity of competent supervisors. Recent studies reveal that, despite supervisory noises, a strong student model may surpass its weak…

Machine Learning · Computer Science 2024-02-26 Yuejiang Liu , Alexandre Alahi

We initiate a unified theoretical and algorithmic study of a key problem in weak-to-strong (W2S) generalization: when fine-tuning a strong pre-trained student with pseudolabels from a weaker teacher on a downstream task with spurious…

Machine Learning · Computer Science 2026-03-23 Chenruo Liu , Yijun Dong , Qi Lei

Weak-to-strong generalization, where a student model trained on imperfect labels generated by a weaker teacher nonetheless surpasses that teacher, has been widely observed but the mechanisms that enable it have remained poorly understood.…

Machine Learning · Statistics 2025-05-27 Behrad Moniri , Hamed Hassani

Currently, machine learning techniques have seen significant success across various applications. Most of these techniques rely on supervision from human-generated labels or a mixture of noisy and imprecise labels from multiple sources.…

Computation and Language · Computer Science 2024-09-04 Yanbo Wang , Wenyu Chen , Shimin Shan

Deep neural networks are gaining increasing popularity for the classic text classification task, due to their strong expressive power and less requirement for feature engineering. Despite such attractiveness, neural text classification…

Information Retrieval · Computer Science 2018-09-13 Yu Meng , Jiaming Shen , Chao Zhang , Jiawei Han