English
Related papers

Related papers: Revisiting Weak-to-Strong Generalization in Theory…

200 papers

Weak-to-strong generalization, where weakly supervised strong models outperform their weaker teachers, offers a promising approach to aligning superhuman models with human values. To deepen the understanding of this approach, we provide…

Machine Learning · Computer Science 2025-06-05 Wei Yao , Wenkai Yang , Gengze Xu , Ziqiao Wang , Yankai Lin , Yong Liu

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…

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

Weak-to-strong generalization (W2SG) has emerged as a promising paradigm for stimulating the capabilities of strong pre-trained models by leveraging supervision from weaker supervisors. To improve the performance of the strong model,…

Machine Learning · Computer Science 2025-06-04 Wei Yao , Gengze Xu , Huayi Tang , Wenkai Yang , Donglin Di , Ziqiao Wang , Yong Liu

Widely used alignment techniques, such as reinforcement learning from human feedback (RLHF), rely on the ability of humans to supervise model behavior - for example, to evaluate whether a model faithfully followed instructions or generated…

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

Aligning powerful AI models on tasks that surpass human evaluation capabilities is the central problem of \textbf{superalignment}. To address this problem, weak-to-strong generalization aims to elicit the capabilities of strong models…

Machine Learning · Computer Science 2025-03-07 Junhao Shi , Qinyuan Cheng , Zhaoye Fei , Yining Zheng , Qipeng Guo , Xipeng Qiu

Weak-to-strong generalization is a phenomenon in post-training whereby a strong student model, when finetuned solely with feedback from a weaker teacher, can not only surpass the teacher, but can improve upon its own capabilities. Recent…

Machine Learning · Computer Science 2026-05-08 Scott Geng , Dutch Hansen , Jerry Li

Weak-to-strong generalization provides a promising paradigm for scaling large language models (LLMs) by training stronger models on samples from aligned weaker ones, without requiring human feedback or explicit reward modeling. However, its…

Computation and Language · Computer Science 2025-10-10 Houcheng Jiang , Junfeng Fang , Jiaxin Wu , Tianyu Zhang , Chen Gao , Yong Li , Xiang Wang , Xiangnan He , Yang Deng

Recent advancements in large language models have sparked interest in their extraordinary and near-superhuman capabilities, leading researchers to explore methods for evaluating and optimizing these abilities, which is called…

Computer Vision and Pattern Recognition · Computer Science 2024-02-07 Jianyuan Guo , Hanting Chen , Chengcheng Wang , Kai Han , Chang Xu , Yunhe Wang

As large language models (LLMs) continue to advance, ensuring their alignment with human values becomes increasingly critical. Traditional alignment methods heavily rely on human feedback to fine-tune models. With the emergence of…

Computation and Language · Computer Science 2025-03-26 Ruimeng Ye , Yang Xiao , Bo Hui

The weak-to-strong generalization phenomenon is the driver for important machine learning applications including highly data-efficient learning and, most recently, performing superalignment. While decades of research have resulted in…

Machine Learning · Computer Science 2025-03-05 Changho Shin , John Cooper , Frederic Sala

It is commonly believed that optimizing the reverse KL divergence results in "mode seeking", while optimizing forward KL results in "mass covering", with the latter being preferred if the goal is to sample from multiple diverse modes. We…

Machine Learning · Computer Science 2025-10-24 Anthony GX-Chen , Jatin Prakash , Jeff Guo , Rob Fergus , Rajesh Ranganath

Large language models (LLMs) are now rapidly advancing and surpassing human abilities on many natural language tasks. However, aligning these super-human LLMs with human knowledge remains challenging because the supervision signals from…

Computation and Language · Computer Science 2024-06-28 Yue Guo , Yi Yang

The paradigm of weak-to-strong generalization constitutes the training of a strong AI model on data labeled by a weak AI model, with the goal that the strong model nevertheless outperforms its weak supervisor on the target task of interest.…

Machine Learning · Computer Science 2025-02-05 Abhijeet Mulgund , Chirag Pabbaraju

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

Advances in large language models raise the question of how alignment techniques will adapt as models become increasingly complex and humans will only be able to supervise them weakly. Weak-to-Strong mimics such a scenario where weak model…

Computation and Language · Computer Science 2025-03-13 Ziyun Cui , Ziyang Zhang , Guangzhi Sun , Wen Wu , Chao Zhang

Weak-to-Strong Generalization (W2SG), where a weak model supervises a stronger one, serves as an important analogy for understanding how humans might guide superhuman intelligence in the future. Promising empirical results revealed that a…

Machine Learning · Computer Science 2025-06-19 Yihao Xue , Jiping Li , Baharan Mirzasoleiman

Recent advances in large language models have shown capabilities that are extraordinary and near-superhuman. These models operate with such complexity that reliably evaluating and aligning them proves challenging for humans. This leads to…

Machine Learning · Computer Science 2024-10-24 Moses Charikar , Chirag Pabbaraju , Kirankumar Shiragur

Aligning large-scale commercial models with user intent is crucial to preventing harmful outputs. Current methods rely on human supervision but become impractical as model complexity increases. When models surpass human knowledge, providing…

Computer Vision and Pattern Recognition · Computer Science 2025-11-25 Jinhao Li , Sarah M. Erfani , Lei Feng , James Bailey , Feng Liu
‹ Prev 1 2 3 10 Next ›