English
Related papers

Related papers: Distilled Self-Critique of LLMs with Synthetic Dat…

200 papers

Synthetic text generation with Differential Privacy (DP) guarantees emerges as a principled approach that can enable the sharing of sensitive datasets across institutional and regulatory boundaries, while bounding the risks of…

Dataset distillation is an advanced technique aimed at compressing datasets into significantly smaller counterparts, while preserving formidable training performance. Significant efforts have been devoted to promote evaluation accuracy…

Computer Vision and Pattern Recognition · Computer Science 2024-10-15 Yifan Wu , Jiawei Du , Ping Liu , Yuewei Lin , Wei Xu , Wenqing Cheng

To collaborate effectively with humans, language models must be able to explain their decisions in natural language. We study a specific type of self-explanation: self-generated counterfactual explanations (SCEs), where a model explains its…

Machine Learning · Computer Science 2025-09-12 Harry Mayne , Ryan Othniel Kearns , Yushi Yang , Andrew M. Bean , Eoin Delaney , Chris Russell , Adam Mahdi

Using huge training datasets can be costly and inconvenient. This article explores various data distillation techniques that can reduce the amount of data required to successfully train deep networks. Inspired by recent ideas, we suggest…

Machine Learning · Computer Science 2022-03-17 Dmitry Medvedev , Alexander D'yakonov

We describe a method for unpaired realistic depth synthesis that learns diverse variations from the real-world depth scans and ensures geometric consistency between the synthetic and synthesized depth. The synthesized realistic depth can…

Computer Vision and Pattern Recognition · Computer Science 2023-08-16 Yuefan Shen , Yanchao Yang , Youyi Zheng , C. Karen Liu , Leonidas Guibas

Semi-supervised learning (SSL) uses unlabeled data for training and has been shown to greatly improve performance when compared to a supervised approach on the labeled data available. This claim depends both on the amount of labeled data…

Machine Learning · Computer Science 2019-10-01 Marc Lelarge , Leo Miolane

Reasoning distillation aims to transfer multi-step reasoning capabilities from large language models to smaller, more efficient ones. While recent methods have shown promising gains, they typically rely on static teacher-student hierarchies…

Machine Learning · Computer Science 2026-05-12 Khouloud Saadi , Di Wang

In deep reinforcement learning (RL), data augmentation is widely considered as a tool to induce a set of useful priors about semantic consistency and improve sample efficiency and generalization performance. However, even when the prior is…

Machine Learning · Computer Science 2023-03-02 Byungchan Ko , Jungseul Ok

In deep reinforcement learning (RL), data augmentation is widely considered as a tool to induce a set of useful priors about semantic consistency and improve sample efficiency and generalization performance. However, even when the prior is…

Machine Learning · Computer Science 2022-10-21 Byungchan Ko , Jungseul Ok

Safe and reliable disclosure of information from confidential data is a challenging statistical problem. A common approach considers the generation of synthetic data, to be disclosed instead of the original data. Efficient approaches ought…

Methodology · Statistics 2024-03-04 Larissa N. A. Martins , Flávio B. Gonçalves , Thais P. Galletti

The aim of dataset distillation is to encode the rich features of an original dataset into a tiny dataset. It is a promising approach to accelerate neural network training and related studies. Different approaches have been proposed to…

Machine Learning · Computer Science 2023-05-30 Zongxiong Chen , Jiahui Geng , Derui Zhu , Herbert Woisetschlaeger , Qing Li , Sonja Schimmler , Ruben Mayer , Chunming Rong

Recently, multi-expert methods have led to significant improvements in long-tail recognition (LTR). We summarize two aspects that need further enhancement to contribute to LTR boosting: (1) More diverse experts; (2) Lower model variance.…

Computer Vision and Pattern Recognition · Computer Science 2023-12-01 Qihao Zhao , Chen Jiang , Wei Hu , Fan Zhang , Jun Liu

Current federated learning algorithms take tens of communication rounds transmitting unwieldy model weights under ideal circumstances and hundreds when data is poorly distributed. Inspired by recent work on dataset distillation and…

Machine Learning · Computer Science 2021-06-08 Yanlin Zhou , George Pu , Xiyao Ma , Xiaolin Li , Dapeng Wu

Recent success of deep learning is largely attributed to the sheer amount of data used for training deep neural networks.Despite the unprecedented success, the massive data, unfortunately, significantly increases the burden on storage and…

Machine Learning · Computer Science 2023-10-10 Ruonan Yu , Songhua Liu , Xinchao Wang

Recent advancements in large language models (LLMs) have significantly enhanced their knowledge and generative capabilities, leading to a surge of interest in leveraging LLMs for high-quality data synthesis. However, synthetic data…

Machine Learning · Computer Science 2025-06-11 Ying Zhou , Xinyao Wang , Yulei Niu , Yaojie Shen , Lexin Tang , Fan Chen , Ben He , Le Sun , Longyin Wen

Offline reinforcement learning often requires a quality dataset that we can train a policy on. However, in many situations, it is not possible to get such a dataset, nor is it easy to train a policy to perform well in the actual environment…

Machine Learning · Computer Science 2025-11-04 Jonathan Light , Yuanzhe Liu , Ziniu Hu

We propose Reinforcement Learning from Contrastive Distillation (RLCD), a method for aligning language models to follow principles expressed in natural language (e.g., to be more harmless) without using human feedback. RLCD creates…

Computation and Language · Computer Science 2024-03-19 Kevin Yang , Dan Klein , Asli Celikyilmaz , Nanyun Peng , Yuandong Tian

On-policy distillation (OPD) has become a popular training paradigm in the LLM community. This paradigm selects a larger model as the teacher to provide dense, fine-grained signals for each sampled trajectory, in contrast to reinforcement…

Machine Learning · Computer Science 2026-04-09 Chenxu Yang , Chuanyu Qin , Qingyi Si , Minghui Chen , Naibin Gu , Dingyu Yao , Zheng Lin , Weiping Wang , Jiaqi Wang , Nan Duan

Diffusion models have achieved remarkable success in generating high-resolution, realistic images across diverse natural distributions. However, their performance heavily relies on high-quality training data, making it challenging to learn…

Machine Learning · Computer Science 2025-05-22 Tianyu Chen , Yasi Zhang , Zhendong Wang , Ying Nian Wu , Oscar Leong , Mingyuan Zhou

Evaluating the quality of generated text automatically remains a significant challenge. Conventional reference-based metrics have been shown to exhibit relatively weak correlation with human evaluations. Recent research advocates the use of…

Computation and Language · Computer Science 2025-11-25 Xiao Wang , Daniil Larionov , Siwei Wu , Yiqi Liu , Steffen Eger , Nafise Sadat Moosavi , Chenghua Lin