English
Related papers

Related papers: Self-Training Doesn't Flatten Language -- It Restr…

200 papers

The pre-training and fine-tuning paradigm has contributed to a number of breakthroughs in Natural Language Processing (NLP). Instead of directly training on a downstream task, language models are first pre-trained on large datasets with…

Machine Learning · Computer Science 2023-08-01 Vithursan Thangarasa , Abhay Gupta , William Marshall , Tianda Li , Kevin Leong , Dennis DeCoste , Sean Lie , Shreyas Saxena

Large language models produce em dashes at varying rates, and the observation that some models "overuse" them has become one of the most widely discussed markers of AI-generated text. Yet no mechanistic account of this pattern exists, and…

Computation and Language · Computer Science 2026-04-01 E. M. Freeburg

Recent studies suggest that very small language models (SLMs) can generate surprisingly coherent text when trained on simplified, child-directed corpora such as TinyStories. These findings have been interpreted as evidence that readability…

Computation and Language · Computer Science 2025-10-17 Ivan Lee , Taylor Berg-Kirkpatrick

This thesis focuses on improving the pre-training of natural language models using unsupervised raw data to make them more efficient and aligned with downstream applications. In the first part, we introduce three alternative pre-training…

Computation and Language · Computer Science 2023-09-18 Luca Di Liello

Due to common architecture designs, symmetries exist extensively in contemporary neural networks. In this work, we unveil the importance of the loss function symmetries in affecting, if not deciding, the learning behavior of machine…

Machine Learning · Computer Science 2024-06-04 Liu Ziyin

Recent supervised fine-tuning (SFT) approaches have significantly improved language models' performance on mathematical reasoning tasks, even when models are trained at a small scale. However, the specific capabilities enhanced through such…

Artificial Intelligence · Computer Science 2026-01-12 Yiyou Sun , Georgia Zhou , Haoyue Bai , Hao Wang , Dacheng Li , Nouha Dziri , Dawn Song

Deep dictionary learning seeks multiple dictionaries at different image scales to capture complementary coherent characteristics. We propose a method for learning a hierarchy of synthesis dictionaries with an image classification goal. The…

Computer Vision and Pattern Recognition · Computer Science 2019-09-04 Shahin Mahdizadehaghdam , Ashkan Panahi , Hamid Krim , Liyi Dai

Text simplification seeks to improve readability while retaining the original content and meaning. Our study investigates whether pre-trained classifiers also maintain such coherence by comparing their predictions on both original and…

Computation and Language · Computer Science 2024-04-11 Miriam Anschütz , Edoardo Mosca , Georg Groh

Self-training, a semi-supervised learning algorithm, leverages a large amount of unlabeled data to improve learning when the labeled data are limited. Despite empirical successes, its theoretical characterization remains elusive. To the…

Machine Learning · Computer Science 2022-02-15 Shuai Zhang , Meng Wang , Sijia Liu , Pin-Yu Chen , Jinjun Xiong

We study how a one-layer attention-only transformer develops relevant structures while learning to sort lists of numbers. At the end of training, the model organizes its attention heads in two main modes that we refer to as…

Machine Learning · Computer Science 2025-02-03 Einar Urdshals , Jasmina Urdshals

Large language models are often viewed as high-dimensional nonlinear systems and treated as black boxes. Here, we show that transformer depth dynamics admit accurate low-order linear surrogates within context. Across tasks including…

Machine Learning · Computer Science 2026-03-16 Buddhika Nettasinghe , Geethu Joseph

Transformers trained on natural language data have been shown to learn its hierarchical structure and generalize to sentences with unseen syntactic structures without explicitly encoding any structural bias. In this work, we investigate…

Computation and Language · Computer Science 2025-03-18 Kabir Ahuja , Vidhisha Balachandran , Madhur Panwar , Tianxing He , Noah A. Smith , Navin Goyal , Yulia Tsvetkov

Synthetic data generated by large language models has become integral to modern NLP training pipelines, from bootstrapping reasoning capabilities to augmenting instruction-following datasets. While recent work demonstrates successful…

Computation and Language · Computer Science 2025-10-08 Y. Du , G. Wu , G. Tang , W. Wang , Q. Fan

Large language models exhibit remarkable performance across diverse tasks through pre-training and fine-tuning paradigms. However, continual fine-tuning on sequential tasks induces catastrophic forgetting, where newly acquired knowledge…

Machine Learning · Computer Science 2026-01-27 Olaf Yunus Laitinen Imanov

We introduce SELF-DISCOVER, a general framework for LLMs to self-discover the task-intrinsic reasoning structures to tackle complex reasoning problems that are challenging for typical prompting methods. Core to the framework is a…

Artificial Intelligence · Computer Science 2024-02-07 Pei Zhou , Jay Pujara , Xiang Ren , Xinyun Chen , Heng-Tze Cheng , Quoc V. Le , Ed H. Chi , Denny Zhou , Swaroop Mishra , Huaixiu Steven Zheng

Post-training fundamentally alters the behavior of large language models (LLMs), yet its impact on the internal parameter space remains poorly understood. In this work, we conduct a systematic singular value decomposition (SVD) analysis of…

Machine Learning · Computer Science 2026-01-30 Xinyu He , Xianghui Cao

To process novel sentences, language models (LMs) must generalize compositionally -- combine familiar elements in new ways. What aspects of a model's structure promote compositional generalization? Focusing on transformers, we test the…

Computation and Language · Computer Science 2024-04-12 Jackson Petty , Sjoerd van Steenkiste , Ishita Dasgupta , Fei Sha , Dan Garrette , Tal Linzen

Language models trained on natural text learn to represent numbers using periodic features with dominant periods at $T=2, 5, 10$. In this paper, we identify a two-tiered hierarchy of these features: while Transformers, Linear RNNs, LSTMs,…

Computation and Language · Computer Science 2026-04-23 Deqing Fu , Tianyi Zhou , Mikhail Belkin , Vatsal Sharan , Robin Jia

Supervised fine-tuning (SFT) is a critical step in aligning large language models (LLMs) with human instructions and values, yet many aspects of SFT remain poorly understood. We trained a wide range of base models on a variety of datasets…

Computation and Language · Computer Science 2025-10-31 Yuto Harada , Yusuke Yamauchi , Yusuke Oda , Yohei Oseki , Yusuke Miyao , Yu Takagi

Evaluating whether large language models (LLMs) capture the structure of natural language beyond local fluency remains an open challenge. Existing evaluation methods, largely based on task performance or short-context behavior, provide…

Computation and Language · Computer Science 2026-05-26 Kumiko Tanaka-Ishii
‹ Prev 1 4 5 6 7 8 10 Next ›