English
Related papers

Related papers: One-shot Entropy Minimization

200 papers

Entropy minimization (EM) trains the model to concentrate even more probability mass on its most confident outputs. We show that this simple objective alone, without any labeled data, can substantially improve large language models' (LLMs)…

Machine Learning · Computer Science 2025-05-22 Shivam Agarwal , Zimin Zhang , Lifan Yuan , Jiawei Han , Hao Peng

In the realm of artificial intelligence, where a vast majority of data is unstructured, obtaining substantial amounts of labeled data to train supervised machine learning models poses a significant challenge. To address this, we delve into…

Machine Learning · Computer Science 2024-01-19 Natan Vidra , Thomas Clifford , Katherine Jijo , Eden Chung , Liang Zhang

Recent advances in reinforcement learning for large language models have converged on increasing complexity: multi-stage training pipelines, dynamic hyperparameter schedules, and curriculum learning strategies. This raises a fundamental…

Computation and Language · Computer Science 2025-12-19 Bingxiang He , Zekai Qu , Zeyuan Liu , Yinghao Chen , Yuxin Zuo , Cheng Qian , Kaiyan Zhang , Weize Chen , Chaojun Xiao , Ganqu Cui , Ning Ding , Zhiyuan Liu

Large pre-trained language models (LMs) have demonstrated remarkable ability as few-shot learners. However, their success hinges largely on scaling model parameters to a degree that makes it challenging to train and serve. In this paper, we…

Computation and Language · Computer Science 2021-05-03 Sinong Wang , Han Fang , Madian Khabsa , Hanzi Mao , Hao Ma

Although large language models (LLMs) have advanced the state-of-the-art in NLP significantly, deploying them for downstream applications is still challenging due to cost, responsiveness, control, or concerns around privacy and security. As…

Computation and Language · Computer Science 2023-11-01 Dong-Ho Lee , Jay Pujara , Mohit Sewak , Ryen W. White , Sujay Kumar Jauhar

We show that reinforcement learning with verifiable reward using one training example (1-shot RLVR) is effective in incentivizing the math reasoning capabilities of large language models (LLMs). Applying RLVR to the base model…

Existing methods to enhance the reasoning capability of large language models predominantly rely on supervised fine-tuning (SFT) followed by reinforcement learning (RL) on reasoning-specific data. These approaches critically depend on…

Machine Learning · Computer Science 2025-05-20 Qingyang Zhang , Haitao Wu , Changqing Zhang , Peilin Zhao , Yatao Bian

Tool-using agents based on Large Language Models (LLMs) excel in tasks such as mathematical reasoning and multi-hop question answering. However, in long trajectories, agents often trigger excessive and low-quality tool calls, increasing…

Artificial Intelligence · Computer Science 2026-03-25 Zeping Li , Hongru Wang , Yiwen Zhao , Guanhua Chen , Yixia Li , Keyang Chen , Yixin Cao , Guangnan Ye , Hongfeng Chai , Zhenfei Yin

To improve deep-learning performance in low-resource settings, many researchers have redesigned model architectures or applied additional data (e.g., external resources, unlabeled samples). However, there have been relatively few…

Computation and Language · Computer Science 2024-07-26 Hongseok Choi , Hyunju Lee

In unsupervised learning, collecting more data is not always a costly process unlike the training. For example, it is not hard to enlarge the 40GB WebText used for training GPT-2 by modifying its sampling methodology considering how many…

Machine Learning · Computer Science 2019-06-18 Aran Komatsuzaki

One of the most impressive results of recent NLP history is the ability of pre-trained language models to solve new tasks in a zero-shot setting. To achieve this, NLP tasks are framed as natural language prompts, generating a response…

Computation and Language · Computer Science 2022-12-29 Chunting Zhou , Junxian He , Xuezhe Ma , Taylor Berg-Kirkpatrick , Graham Neubig

Recent work in incremental learning has introduced diverse approaches to tackle catastrophic forgetting from data augmentation to optimized training regimes. However, most of them focus on very few training steps. We propose a method for…

Computation and Language · Computer Science 2022-10-27 Karan Praharaj , Irina Matveeva

Reinforcement learning (RL) has enabled machine learning models to achieve significant advances in many fields. Most recently, RL has empowered frontier language models to solve challenging math, science, and coding problems. However,…

Machine Learning · Computer Science 2025-06-30 Mihir Prabhudesai , Lili Chen , Alex Ippoliti , Katerina Fragkiadaki , Hao Liu , Deepak Pathak

As access to high-quality, domain-specific data grows increasingly scarce, multi-epoch training has become a practical strategy for adapting large language models (LLMs). However, autoregressive models often suffer from performance…

Computation and Language · Computer Science 2025-12-30 Jiapeng Wang , Yiwen Hu , Yanzipeng Gao , Haoyu Wang , Shuo Wang , Hongyu Lu , Jiaxin Mao , Wayne Xin Zhao , Junyi Li , Xiao Zhang

Large Reasoning Models (LRMs) often suffer from overthinking, generating unnecessarily long reasoning chains even for simple tasks. This leads to substantial computational overhead with limited performance gain, primarily due to redundant…

Artificial Intelligence · Computer Science 2026-01-13 Ruichu Cai , Haopeng Du , Qingwen Lin , Yutong Chen , Zijian Li , Boyan Xu

Few-shot learning benchmarks are critical for evaluating modern NLP techniques. It is possible, however, that benchmarks favor methods which easily make use of unlabeled text, because researchers can use unlabeled text from the test set to…

Computation and Language · Computer Science 2024-10-03 Kush Dubey

Meta-learning is a powerful paradigm for tackling few-shot tasks. However, recent studies indicate that models trained with the whole-class training strategy can achieve comparable performance to those trained with meta-learning in few-shot…

Machine Learning · Computer Science 2025-09-17 Yunchuan Guan , Yu Liu , Ke Zhou , Zhiqi Shen , Jenq-Neng Hwang , Serge Belongie , Lei Li

Deep neural networks require large training sets but suffer from high computational cost and long training times. Training on much smaller training sets while maintaining nearly the same accuracy would be very beneficial. In the few-shot…

Machine Learning · Computer Science 2021-08-09 Ilia Sucholutsky , Matthias Schonlau

The field of machine learning has recently made significant progress in reducing the requirements for labelled training data when building new models. These `cheaper' learning techniques hold significant potential for the social sciences,…

Computation and Language · Computer Science 2025-07-29 Leonardo Castro-Gonzalez , Yi-Ling Chung , Hannak Rose Kirk , John Francis , Angus R. Williams , Pica Johansson , Jonathan Bright

Learning from a few examples remains a key challenge in machine learning. Despite recent advances in important domains such as vision and language, the standard supervised deep learning paradigm does not offer a satisfactory solution for…

Machine Learning · Computer Science 2018-01-01 Oriol Vinyals , Charles Blundell , Timothy Lillicrap , Koray Kavukcuoglu , Daan Wierstra
‹ Prev 1 2 3 10 Next ›