中文
相关论文

相关论文: Discrepancies are Virtue: Weak-to-Strong Generaliz…

200 篇论文

Weak-to-strong (W2S) generalization, in which a strong model is fine-tuned on outputs of a weaker, task-specialized model, has been proposed as an approach to aligning superhuman AI systems. Existing theoretical analyses either fix the…

机器学习 · 统计学 2026-05-14 Ryoya Awano , Taiji Suzuki

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…

机器学习 · 计算机科学 2026-03-23 Chenruo Liu , Yijun Dong , Qi Lei

Weak-to-Strong Generalization (Burns et al., 2024) is the phenomenon whereby a strong student, say GPT-4, learns a task from a weak teacher, say GPT-2, and ends up significantly outperforming the teacher. We show that this phenomenon does…

机器学习 · 计算机科学 2025-11-11 Marko Medvedev , Kaifeng Lyu , Dingli Yu , Sanjeev Arora , Zhiyuan Li , Nathan Srebro

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…

机器学习 · 计算机科学 2025-09-30 Gengze Xu , Wei Yao , Ziqiao Wang , Yong 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…

机器学习 · 计算机科学 2026-05-08 Scott Geng , Dutch Hansen , Jerry Li

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,…

机器学习 · 计算机科学 2024-05-28 Hunter Lang , David Sontag , Aravindan Vijayaraghavan

The classic teacher-student model in machine learning posits that a strong teacher supervises a weak student to improve the student's capabilities. We instead consider the inverted situation, where a weak teacher supervises a strong student…

机器学习 · 计算机科学 2025-02-03 David X. Wu , Anant Sahai

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,…

机器学习 · 计算机科学 2025-06-04 Wei Yao , Gengze Xu , Huayi Tang , Wenkai Yang , Donglin Di , Ziqiao Wang , Yong Liu

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.…

机器学习 · 统计学 2025-05-27 Behrad Moniri , Hamed Hassani

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…

机器学习 · 计算机科学 2025-06-19 Yihao Xue , Jiping Li , Baharan Mirzasoleiman

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…

机器学习 · 计算机科学 2025-10-30 Junsoo Oh , Jerry Song , Chulhee Yun

With Large Language Models (LLMs) rapidly approaching and potentially surpassing human-level performance, it has become imperative to develop approaches capable of effectively supervising and enhancing these powerful models using smaller,…

With Large Language Models (LLMs) rapidly approaching and potentially surpassing human-level performance, it has become imperative to develop approaches capable of effectively supervising and enhancing these powerful models using smaller,…

Weak-to-strong (W2S) generalization is a promising framework for scalable oversight, yet existing evaluations often test students under matched train-test distributions. Therefore, we study W2S preference learning under zero-shot…

计算与语言 · 计算机科学 2026-05-27 Khoi Le , Tri Cao , Phong Nguyen , Cong-Duy Nguyen , Anh Tuan Luu , Miao Chunyan , See-Kiong Ng , Thong Nguyen

The rapid proliferation of generative AI, especially large language models, has led to their integration into a variety of applications. A key phenomenon known as weak-to-strong generalization - where a strong model trained on a weak…

机器学习 · 计算机科学 2025-01-03 Martin Pawelczyk , Lillian Sun , Zhenting Qi , Aounon Kumar , Himabindu Lakkaraju

It is increasingly common in machine learning to use learned models to label data and then employ such data to train more capable models. The phenomenon of weak-to-strong generalization exemplifies the advantage of this two-stage procedure:…

机器学习 · 计算机科学 2026-05-26 Diyuan Wu , Lehan Chen , Theodor Misiakiewicz , Marco Mondelli

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…

机器学习 · 计算机科学 2024-10-24 Moses Charikar , Chirag Pabbaraju , Kirankumar Shiragur

The paradigm of Weak-to-Strong Generalization (W2SG) suggests that a pre-trained strong model can surpass its weak supervisor, yet the decisive role of pre-training remains theoretically and empirically under-explored. In this work, we…

机器学习 · 计算机科学 2026-05-08 Wei Yao , Wang Zhaoyang , Gengze Xu , Chen Qian , Dongrui Liu , Ziqiao Wang , Yong Liu , Yunbei Xu

Weak-to-Strong generalization (W2SG) is a new trend to elicit the full capabilities of a strong model with supervision from a weak model. While existing W2SG studies focus on simple tasks like binary classification, we extend this paradigm…

机器学习 · 计算机科学 2026-03-10 Ruimeng Ye , Zihan Wang , Yang Xiao , Zinan Ling , Manling Li , Bo Hui

The goal of diffusion generative models is to align the learned distribution with the real data distribution through gradient score matching. However, inherent limitations in training data quality, modeling strategies, and architectural…

机器学习 · 计算机科学 2025-04-25 Lichen Bai , Masashi Sugiyama , Zeke Xie
‹ 上一页 1 2 3 10 下一页 ›