English
Related papers

Related papers: Shall Your Data Strategy Work? Perform a Swift Stu…

200 papers

Large-scale black-box models have become ubiquitous across numerous applications. Understanding the influence of individual training data sources on predictions made by these models is crucial for improving their trustworthiness. Current…

Machine Learning · Computer Science 2024-06-21 Myeongseob Ko , Feiyang Kang , Weiyan Shi , Ming Jin , Zhou Yu , Ruoxi Jia

Fine-tuning large language models (LLMs) on chain-of-thought (CoT) data shows that a small amount of high-quality data can outperform massive datasets. Yet, what constitutes "quality" remains ill-defined. Existing reasoning methods rely on…

Machine Learning · Computer Science 2025-12-02 Prateek Humane , Paolo Cudrano , Daniel Z. Kaplan , Matteo Matteucci , Supriyo Chakraborty , Irina Rish

We propose GradTail, an algorithm that uses gradients to improve model performance on the fly in the face of long-tailed training data distributions. Unlike conventional long-tail classifiers which operate on converged - and possibly…

Machine Learning · Computer Science 2022-01-20 Zhao Chen , Vincent Casser , Henrik Kretzschmar , Dragomir Anguelov

As the post-training of large language models (LLMs) advances from instruction-following to complex reasoning tasks, understanding how different data affect finetuning dynamics remains largely unexplored. In this paper, we present a…

Machine Learning · Computer Science 2026-05-12 Ming Li , Yanhong Li , Ziyue Li , Tianyi Zhou

Policy gradient methods are among the most effective methods for large-scale reinforcement learning, and their empirical success has prompted several works that develop the foundation of their global convergence theory. However, prior works…

Machine Learning · Computer Science 2020-12-25 Junzi Zhang , Jongho Kim , Brendan O'Donoghue , Stephen Boyd

While large language models (LLMs) demonstrate reasonable zero-shot capability across many downstream tasks, fine-tuning is a common practice to improve their performance. However, a task's data efficiency--i.e., the number of fine-tuning…

Machine Learning · Computer Science 2026-01-01 Gyung Hyun Je , Colin Raffel

Influence estimation analyzes how changes to the training data can lead to different model predictions; this analysis can help us better understand these predictions, the models making those predictions, and the data sets they're trained…

Machine Learning · Computer Science 2023-06-01 Jonathan Brophy , Zayd Hammoudeh , Daniel Lowd

Having a sufficient quantity of quality data is a critical enabler of training effective machine learning models. Being able to effectively determine the adequacy of a dataset prior to training and evaluating a model's performance would be…

Machine Learning · Computer Science 2026-04-28 Arya Hatamian , Lionel Levine , Haniyeh Ehsani Oskouie , Majid Sarrafzadeh

Reasoning post-training improves Large Language Models (LLMs) on complex tasks such as mathematics and coding, but its benefits across diverse multimodal tasks remains uncertain. The trend of releasing parallel "Instruct" and "Thinking"…

Computation and Language · Computer Science 2026-05-12 Ruobing Zheng , Tianqi Li , Jianing Li , Qingpei Guo , Yi Yuan , Jingdong Chen

Chain-of-thought (CoT) reasoning is useful for monitoring language models only when the reasoning trace faithfully reflects the computation that produces the final answer. However, models can rely on prompt-to-answer shortcuts that bypass…

Machine Learning · Computer Science 2026-05-26 Jinghan Jia , Joe Benton , Eric Easley

The Chain-of-Thought (CoT) paradigm has emerged as a critical approach for enhancing the reasoning capabilities of large language models (LLMs). However, despite their widespread adoption and success, CoT methods often exhibit instability…

Artificial Intelligence · Computer Science 2024-09-06 Yu Wang , Shiwan Zhao , Zhihu Wang , Heyuan Huang , Ming Fan , Yubo Zhang , Zhixing Wang , Haijun Wang , Ting Liu

Training data influence estimation methods quantify the contribution of training documents to a model's output, making them a promising source of information for example-based explanations. As humans cannot interpret thousands of documents,…

Computation and Language · Computer Science 2026-04-10 Loris Schoenegger , Benjamin Roth

The great success of deep learning heavily relies on increasingly larger training data, which comes at a price of huge computational and infrastructural costs. This poses crucial questions that, do all training data contribute to model's…

Machine Learning · Computer Science 2023-02-28 Shuo Yang , Zeke Xie , Hanyu Peng , Min Xu , Mingming Sun , Ping Li

Gradient-based iterative optimization methods are the workhorse of modern machine learning. They crucially rely on careful tuning of parameters like learning rate and momentum. However, one typically sets them using heuristic approaches…

Machine Learning · Computer Science 2025-12-05 Dravyansh Sharma

As LLMs continue to scale, improving training efficiency increasingly depends on using data more effectively. Data selection addresses this problem by allocating a limited training budget to samples that best promote a target behavior.…

Machine Learning · Computer Science 2026-05-21 Qihao Lin , Guanxu Chen , Dongrui Liu , Jing Shao

Data cleansing is a typical approach used to improve the accuracy of machine learning models, which, however, requires extensive domain knowledge to identify the influential instances that affect the models. In this paper, we propose an…

Machine Learning · Statistics 2019-06-21 Satoshi Hara , Atsushi Nitanda , Takanori Maehara

In many recent applications, data is plentiful. By now, we have a rather clear understanding of how more data can be used to improve the accuracy of learning algorithms. Recently, there has been a growing interest in understanding how more…

Machine Learning · Computer Science 2011-06-16 Shai Shalev-Shwartz , Ohad Shamir , Eran Tromer

We focus on developing efficient and reliable policy optimization strategies for robot learning with real-world data. In recent years, policy gradient methods have emerged as a promising paradigm for training control policies in simulation.…

Machine Learning · Computer Science 2023-11-07 Tyler Westenbroek , Jacob Levy , David Fridovich-Keil

Datasets nowadays are generally constructed from multiple sources and using different synthetic techniques, making data de-noising and de-duplication crucial before being used for post-training. In this work, we propose to perform…

Computation and Language · Computer Science 2024-12-24 Qi Jia , Siyu Ren , Ziheng Qin , Fuzhao Xue , Jinjie Ni , Yang You

Data mining methods have been widely applied in financial markets, with the purpose of providing suitable tools for prices forecasting and automatic trading. Particularly, learning methods aim to identify patterns in time series and, based…

Machine Learning · Statistics 2013-01-22 Marcelo S. Lauretto , Barbara B. C. Silva , Pablo M. Andrade