English
Related papers

Related papers: WST: Weak-to-Strong Knowledge Transfer via Reinfor…

200 papers

The Recurrent Neural Network-Transducer (RNN-T) is widely adopted in end-to-end (E2E) automatic speech recognition (ASR) tasks but depends heavily on large-scale, high-quality annotated data, which are often costly and difficult to obtain.…

Computation and Language · Computer Science 2025-11-07 Dongji Gao , Chenda Liao , Changliang Liu , Matthew Wiesner , Leibny Paola Garcia , Daniel Povey , Sanjeev Khudanpur , Jian Wu

Large language models (LLMs) can acquire strong code-generation capabilities through few-shot learning. In contrast, supervised fine-tuning is still needed for smaller models to achieve good performance. Such fine-tuning demands a large…

Computation and Language · Computer Science 2023-06-09 Zhangir Azerbayev , Ansong Ni , Hailey Schoelkopf , Dragomir Radev

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…

Machine Learning · Computer Science 2025-11-11 Marko Medvedev , Kaifeng Lyu , Dingli Yu , Sanjeev Arora , Zhiyuan Li , Nathan Srebro

Reinforcement learning from human feedback (RLHF) can improve the quality of large language model's (LLM) outputs by aligning them with human preferences. We propose a simple algorithm for aligning LLMs with human preferences inspired by…

The growing capabilities of large language models (LLMs) present a key challenge of maintaining effective human oversight. Weak-to-strong generalization (W2SG) offers a promising framework for supervising increasingly capable LLMs using…

Computation and Language · Computer Science 2025-04-15 Shujin Wu , Cheng Qian , Yi R. Fung , Paul Pu Liang , Heng Ji

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…

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…

Distillation from Weak Teacher (DWT) is a method of transferring knowledge from a smaller, weaker teacher model to a larger student model to improve its performance. Previous studies have shown that DWT can be effective in the vision domain…

Computation and Language · Computer Science 2023-05-30 Hayeon Lee , Rui Hou , Jongpil Kim , Davis Liang , Sung Ju Hwang , Alexander Min

In recent years, the growing interest in Large Language Models (LLMs) has significantly advanced prompt engineering, transitioning from manual design to model-based optimization. Prompts for LLMs generally comprise two components: the…

Computation and Language · Computer Science 2025-10-09 Qinhao Zhou , Xiang Xiang , Kun He , John E. Hopcroft

Large Language Models (LLMs) face the "knowledge cutoff" challenge, where their frozen parametric memory prevents direct internalization of new information. While Supervised Fine-Tuning (SFT) is commonly used to update model knowledge, it…

Machine Learning · Computer Science 2026-05-12 Pingzhi Tang , Yiding Wang , Muhan Zhang

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

This paper addresses the limited transfer and adaptation capabilities of large language models in low-resource language scenarios. It proposes a unified framework that combines a knowledge transfer module with parameter-efficient…

Computation and Language · Computer Science 2025-07-03 Shuangquan Lyu , Yingnan Deng , Guiran Liu , Zhen Qi , Ruotong Wang

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…

Machine Learning · Statistics 2026-05-14 Ryoya Awano , Taiji Suzuki

Well-designed prompts can guide text-to-image models to generate amazing images. However, the performant prompts are often model-specific and misaligned with user input. Instead of laborious human engineering, we propose prompt adaptation,…

Computation and Language · Computer Science 2024-01-01 Yaru Hao , Zewen Chi , Li Dong , Furu Wei

Prompt engineering is critical for the development of LLM-based applications. However, it is usually done manually in a "trial and error" fashion that can be time consuming, ineffective, and sub-optimal. Even for the prompts which seemingly…

Artificial Intelligence · Computer Science 2024-06-11 Weize Kong , Spurthi Amba Hombaiah , Mingyang Zhang , Qiaozhu Mei , Michael Bendersky

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

Efficient fine-tuning of large language models for task-specific applications is imperative, yet the vast number of parameters in these models makes their training increasingly challenging. Despite numerous proposals for effective methods,…

Computation and Language · Computer Science 2024-10-15 Chenghao Fan , Zhenyi Lu , Wei Wei , Jie Tian , Xiaoye Qu , Dangyang Chen , Yu Cheng

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,…

Machine Learning · Computer Science 2025-07-24 Aakriti Agrawal , Mucong Ding , Zora Che , Chenghao Deng , Anirudh Satheesh , Bang An , Bayan Bruss , John Langford , Furong Huang

This paper presents a framework based on Weighted Finite-State Transducers (WFST) to simplify the development of modifications for RNN-Transducer (RNN-T) loss. Existing implementations of RNN-T use CUDA-related code, which is hard to extend…

Audio and Speech Processing · Electrical Eng. & Systems 2023-05-10 Aleksandr Laptev , Vladimir Bataev , Igor Gitman , Boris Ginsburg

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
‹ Prev 1 2 3 10 Next ›