English
Related papers

Related papers: EnsemW2S: Enhancing Weak-to-Strong Generalization …

200 papers

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…

Pretrained large language models (LLMs) are currently state-of-the-art for solving the vast majority of natural language processing tasks. While many real-world applications still require fine-tuning to reach satisfactory levels of…

Weak supervision (WS) frameworks are a popular way to bypass hand-labeling large datasets for training data-hungry models. These approaches synthesize multiple noisy but cheaply-acquired estimates of labels into a set of high-quality…

Machine Learning · Computer Science 2023-11-30 Changho Shin , Winfred Li , Harit Vishwakarma , Nicholas Roberts , Frederic Sala

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-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

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

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

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

Large language models (LLMs) have achieved remarkable proficiency on solving diverse problems. However, their generalization ability is not always satisfying and the generalization problem is common for generative transformer models in…

Machine Learning · Computer Science 2024-08-20 Xingcheng Xu , Zihao Pan , Haipeng Zhang , Yanqing Yang

How can we train models to perform well on hard test data when hard training data is by definition difficult to label correctly? This question has been termed the scalable oversight problem and has drawn increasing attention as language…

Computation and Language · Computer Science 2024-06-06 Peter Hase , Mohit Bansal , Peter Clark , Sarah Wiegreffe

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

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

The performance of deep learning-based natural language processing systems is based on large amounts of labeled training data which, in the clinical domain, are not easily available or affordable. Weak supervision and in-context learning…

Computation and Language · Computer Science 2025-04-02 Enshuo Hsu , Kirk Roberts

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

Large language models (LLMs) have demonstrated strong machine translation capabilities for English-centric language pairs but underperform in direct non-English (x2x) translation. This work addresses this limitation through a synthetic data…

Computation and Language · Computer Science 2025-09-25 Sen Yang , Yu Bao , Yu Lu , Jiajun Chen , Shujian Huang , Shanbo Cheng

Common methods for aligning already-capable models with desired behavior rely on the ability of humans to provide supervision. However, future superhuman models will surpass the capability of humans. Therefore, humans will only be able to…

Computation and Language · Computer Science 2025-01-24 Hao Lang , Fei Huang , Yongbin Li

How can "weak teacher models" such as average human annotators or existing AI systems, effectively supervise LLMs to improve performance on hard reasoning tasks, especially those that challenge and requires expertise or daily practice from…

Machine Learning · Computer Science 2025-02-26 Xuan He , Da Yin , Nanyun Peng

Efficiently leveraging of the capabilities of contemporary large language models (LLMs) is increasingly challenging, particularly when direct fine-tuning is expensive and often impractical. Existing training-free methods, including manually…

Artificial Intelligence · Computer Science 2025-04-08 Fan Nie , Lan Feng , Haotian Ye , Weixin Liang , Pan Lu , Huaxiu Yao , Alexandre Alahi , James Zou

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…

Machine Learning · Computer Science 2025-02-03 David X. Wu , Anant Sahai

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