English
Related papers

Related papers: Improving Weak-to-Strong Generalization with Scala…

200 papers

The rapid advancement of artificial intelligence systems has brought the challenge of AI alignment to the forefront of research, particularly in complex decision-making and task execution. As these systems surpass human-level performance in…

Artificial Intelligence · Computer Science 2024-09-12 Mehrdad Zakershahrak , Samira Ghodratnama

We have witnessed superhuman intelligence thanks to the fast development of large language models and multimodal language models. As the application of such superhuman models becomes more and more popular, a critical question arises here:…

Computation and Language · Computer Science 2024-12-24 Minlie Huang , Yingkang Wang , Shiyao Cui , Pei Ke , Jie Tang

Current AI alignment methodologies rely on human-provided demonstrations or judgments, and the learned capabilities of AI systems would be upper-bounded by human capabilities as a result. This raises a challenging research question: How can…

Machine Learning · Computer Science 2024-12-11 Zhiqing Sun , Longhui Yu , Yikang Shen , Weiyang Liu , Yiming Yang , Sean Welleck , Chuang Gan

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

The emergence of large language models (LLMs) has sparked the possibility of about Artificial Superintelligence (ASI), a hypothetical AI system surpassing human intelligence. However, existing alignment paradigms struggle to guide such…

Machine Learning · Computer Science 2024-12-30 HyunJin Kim , Xiaoyuan Yi , Jing Yao , Jianxun Lian , Muhua Huang , Shitong Duan , JinYeong Bak , Xing Xie

Weak-to-strong (W2S) generalization is a type of finetuning (FT) where a strong (large) student model is trained on pseudo-labels generated by a weak teacher. Surprisingly, W2S FT often outperforms the weak teacher. We seek to understand…

Machine Learning · Computer Science 2026-04-21 Yijun Dong , Yicheng Li , Yunai Li , Jason D. Lee , Qi Lei

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

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 alignment offers a promising route to scalable supervision, but it can fail when a strong model becomes confidently wrong on examples that lie in the weak teacher's blind spots. Understanding such failures requires going…

Artificial Intelligence · Computer Science 2026-04-29 Hamid Osooli , Kareema Batool , Rick Gentry , Tiasa Singha Roy , Ashwin Gupta , Anirudha Ramesh

Supervised Learning is a way of developing Artificial Intelligence systems in which a computer algorithm is trained on labeled data inputs. Effectiveness of a Supervised Learning algorithm is determined by its performance on a given dataset…

Computers and Society · Computer Science 2024-10-29 Shubhi Bansal , Atharva Tendulkar , Nagendra Kumar

As Artificial Intelligence (AI) advances toward Artificial General Intelligence (AGI) and eventually Artificial Superintelligence (ASI), it may potentially surpass human control, deviate from human values, and even lead to irreversible…

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…

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

When large language models (LLMs) exceed human-level capabilities, it becomes increasingly challenging to provide full-scale and accurate supervision for these models. Weak-to-strong learning, which leverages a less capable model to unlock…

Computation and Language · Computer Science 2024-10-02 Yuqing Yang , Yan Ma , Pengfei Liu

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

Weakly supervised learning generally faces challenges in applicability to various scenarios with diverse weak supervision and in scalability due to the complexity of existing algorithms, thereby hindering the practical deployment. This…

Machine Learning · Computer Science 2024-06-06 Hao Chen , Jindong Wang , Lei Feng , Xiang Li , Yidong Wang , Xing Xie , Masashi Sugiyama , Rita Singh , Bhiksha Raj

Diffusion models generate synthetic images through an iterative refinement process. However, the misalignment between the simulation-free objective and the iterative process often causes accumulated gradient error along the sampling…

Computer Vision and Pattern Recognition · Computer Science 2026-03-24 Liangyu Yuan , Yufei Huang , Mingkun Lei , Tong Zhao , Ruoyu Wang , Changxi Chi , Yiwei Wang , Chi Zhang

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

As Large Language Models increasingly automate complex, long-horizon tasks such as \emph{vibe coding}, a supervision gap has emerged. While models excel at execution, users often struggle to guide them effectively due to insufficient domain…

Artificial Intelligence · Computer Science 2026-02-09 Enyu Zhou , Zhiheng Xi , Long Ma , Zhihao Zhang , Shihan Dou , Zhikai Lei , Guoteng Wang , Rui Zheng , Hang Yan , Tao Gui , Qi Zhang , Xuanjing Huang

Applied mathematics and machine computations have raised a lot of hope since the recent success of supervised learning. Many practitioners in industries have been trying to switch from their old paradigms to machine learning. Interestingly,…

Machine Learning · Computer Science 2022-09-26 Vivien Cabannes