English
Related papers

Related papers: Quantifying the Gain in Weak-to-Strong Generalizat…

200 papers

Recent studies show that pretraining a deep neural network with fine-grained labeled data, followed by fine-tuning on coarse-labeled data for downstream tasks, often yields better generalization than pretraining with coarse-labeled data.…

Machine Learning · Computer Science 2024-12-11 Guan Zhe Hong , Yin Cui , Ariel Fuxman , Stanley Chan , Enming Luo

Large pre-trained language models (LMs) such as GPT-3 have acquired a surprising ability to perform zero-shot learning. For example, to classify sentiment without any training examples, we can "prompt" the LM with the review and the label…

Computation and Language · Computer Science 2021-09-09 Ruiqi Zhong , Kristy Lee , Zheng Zhang , Dan Klein

Large language models (LLMs) are increasingly used in decision-making contexts, but when they present answers without signaling low confidence, users may unknowingly act on erroneous outputs. Prior work shows that LLMs maintain internal…

Computation and Language · Computer Science 2025-10-23 Mark Steyvers , Catarina Belem , Padhraic Smyth

Overfitting is a phenomenon that occurs when a machine learning model is trained for too long and focused too much on the exact fitness of the training samples to the provided training labels and cannot keep track of the predictive rules…

Machine Learning · Computer Science 2025-09-22 Nuri Korhan , Samet Bayram

A recently-proposed technique called self-adaptive training augments modern neural networks by allowing them to adjust training labels on the fly, to avoid overfitting to samples that may be mislabeled or otherwise non-representative. By…

Machine Learning · Computer Science 2020-06-16 Daniel Chiu , Franklyn Wang , Scott Duke Kominers

In this work, we study the computational complexity of determining whether a machine learning model that perfectly fits the training data will generalizes to unseen data. In particular, we study the power of a malicious agent whose goal is…

Machine Learning · Computer Science 2022-03-25 Ankur Moitra , Elchanan Mossel , Colin Sandon

The correct specification of reward models is a well-known challenge in reinforcement learning. Hand-crafted reward functions often lead to inefficient or suboptimal policies and may not be aligned with user values. Reinforcement learning…

Artificial Intelligence · Computer Science 2024-10-24 Muhan Lin , Shuyang Shi , Yue Guo , Behdad Chalaki , Vaishnav Tadiparthi , Ehsan Moradi Pari , Simon Stepputtis , Joseph Campbell , Katia Sycara

Large language models have achieved significant reasoning improvements through reinforcement learning with verifiable rewards (RLVR). Yet as model capabilities grow, constructing high-quality reward signals becomes increasingly difficult,…

Machine Learning · Computer Science 2026-04-21 Salman Rahman , Jingyan Shen , Anna Mordvina , Hamid Palangi , Saadia Gabriel , Pavel Izmailov

Autoregressive language models like GPT aim to predict next tokens, while autoencoding models such as BERT are trained on tasks such as predicting masked tokens. We train a decoder-only architecture for predicting the second to last token…

Computation and Language · Computer Science 2025-02-17 Johannes Schneider

Recent empirical studies have explored the idea of continuing to train a model at test-time for a given task, known as test-time training (TTT), and have found it to yield significant performance improvements. However, there is limited…

Machine Learning · Computer Science 2026-02-10 Jonas Hübotter , Patrik Wolf , Alexander Shevchenko , Dennis Jüni , Andreas Krause , Gil Kur

Datasets typically contain inaccuracies due to human error and societal biases, and these inaccuracies can affect the outcomes of models trained on such datasets. We present a technique for certifying whether linear regression models are…

Machine Learning · Computer Science 2022-06-09 Anna P. Meyer , Aws Albarghouthi , Loris D'Antoni

Owing to the prohibitive costs of generating large amounts of labeled data, programmatic weak supervision is a growing paradigm within machine learning. In this setting, users design heuristics that provide noisy labels for subsets of the…

Machine Learning · Computer Science 2023-10-06 Dylan Sam , J. Zico Kolter

Current language models are considered to have sub-human capabilities at natural language tasks like question-answering or writing code. However, language models are not trained to perform well at these tasks, they are trained to accurately…

Computation and Language · Computer Science 2024-07-16 Buck Shlegeris , Fabien Roger , Lawrence Chan , Euan McLean

One-hot labels do not represent soft decision boundaries among concepts, and hence, models trained on them are prone to overfitting. Using soft labels as targets provide regularization, but different soft labels might be optimal at…

Machine Learning · Computer Science 2020-09-22 Nidhi Vyas , Shreyas Saxena , Thomas Voice

Large language models (LLMs) have shown remarkable adaptability to diverse tasks, by leveraging context prompts containing instructions, or minimal input-output examples. However, recent work revealed they also exhibit label bias -- an…

Computation and Language · Computer Science 2024-05-07 Yuval Reif , Roy Schwartz

Large Language Models (LLMs) display strikingly different generalization behaviors: supervised fine-tuning (SFT) often narrows capability, whereas reinforcement-learning (RL) tuning tends to preserve it. The reasons behind this divergence…

Machine Learning · Computer Science 2026-01-01 Haoyue Bai , Yiyou Sun , Wenjie Hu , Shi Qiu , Maggie Ziyu Huan , Peiyang Song , Robert Nowak , Dawn Song

Most large language models are fine-tuned using either expensive human-annotated data or GPT-4 generated data which cannot guarantee performance in certain domains. We argue that although the web-crawled data often has formatting errors…

Computation and Language · Computer Science 2024-08-16 Jing Zhou , Chenglin Jiang , Wei Shen , Xiao Zhou , Xiaonan He

Current pre-trained language models have enabled remarkable improvements in downstream tasks, but it remains difficult to distinguish effects of statistical correlation from more systematic logical reasoning grounded on the understanding of…

Computation and Language · Computer Science 2023-05-29 Jiaxuan Li , Lang Yu , Allyson Ettinger

Programmatic weak supervision creates models without hand-labeled training data by combining the outputs of heuristic labelers. Existing frameworks make the restrictive assumption that labelers output a single class label. Enabling users to…

Machine Learning · Computer Science 2022-03-28 Peilin Yu , Tiffany Ding , Stephen H. Bach

Weak supervision is leveraged in a wide range of domains and tasks due to its ability to create massive amounts of labeled data, requiring only little manual effort. Standard approaches use labeling functions to specify signals that are…

Machine Learning · Computer Science 2022-11-23 Luisa März , Ehsaneddin Asgari , Fabienne Braune , Franziska Zimmermann , Benjamin Roth