English
Related papers

Related papers: Transformers Simulate MLE for Sequence Generation …

200 papers

Recursive processing is considered a hallmark of human linguistic abilities. A recent study evaluated recursive processing in recurrent neural language models (RNN-LMs) and showed that such models perform below chance level on embedded…

Computation and Language · Computer Science 2021-10-15 Yair Lakretz , Théo Desbordes , Dieuwke Hupkes , Stanislas Dehaene

While large language models based on the transformer architecture have demonstrated remarkable in-context learning (ICL) capabilities, understandings of such capabilities are still in an early stage, where existing theory and mechanistic…

Machine Learning · Computer Science 2023-10-17 Tianyu Guo , Wei Hu , Song Mei , Huan Wang , Caiming Xiong , Silvio Savarese , Yu Bai

The transformer neural network architecture allows for autoregressive sequence-to-sequence modeling through the use of attention layers. It was originally created with the application of machine translation but has revolutionized natural…

Computer Vision and Pattern Recognition · Computer Science 2024-06-25 Abhi Kamboj

Time series forecasting is crucial for many fields, such as disaster warning, weather prediction, and energy consumption. The Transformer-based models are considered to have revolutionized the field of sequence modeling. However, the…

Machine Learning · Computer Science 2022-11-01 Junlong Tong , Liping Xie , Wankou Yang , Kanjian Zhang

Sequence-to-sequence models are commonly trained via maximum likelihood estimation (MLE). However, standard MLE training considers a word-level objective, predicting the next word given the previous ground-truth partial sentence. This…

Computation and Language · Computer Science 2019-01-21 Liqun Chen , Yizhe Zhang , Ruiyi Zhang , Chenyang Tao , Zhe Gan , Haichao Zhang , Bai Li , Dinghan Shen , Changyou Chen , Lawrence Carin

In-context learning enables transformer models to generalize to new tasks based solely on input prompts, without any need for weight updates. However, existing training paradigms typically rely on large, unstructured datasets that are…

We investigate the capacity of transformers to learn algorithms involving their context while solely being trained using next token prediction. We set up Markov chains with random transition matrices and we train transformers to predict the…

Machine Learning · Computer Science 2025-08-07 Simon Lepage , Jeremie Mary , David Picard

Large language models (LLMs) have initiated a paradigm shift in transfer learning. In contrast to the classic pretraining-then-finetuning procedure, in order to use LLMs for downstream prediction tasks, one only needs to provide a few…

Computation and Language · Computer Science 2025-09-16 Chi Han , Ziqi Wang , Han Zhao , Heng Ji

This paper introduces a novel framework that leverages large language models (LLMs) for machine translation (MT). We start with one conjecture: an ideal translation should contain complete and accurate information for a strong enough LLM to…

Computation and Language · Computer Science 2024-11-06 Jianqiao Wangni

Large language models (LLMs) have reached human-like proficiency in generating diverse textual content, underscoring the necessity for effective fake text detection to avoid potential risks such as fake news in social media. Previous…

Machine Learning · Computer Science 2024-03-21 Zhixin Lai , Xuesheng Zhang , Suiyao Chen

Large language models (LLMs) are increasingly used as agents that interact with users and with the world. To do so successfully, LLMs must construct representations of the world and form probabilistic beliefs about them. To provide…

Computation and Language · Computer Science 2026-01-16 Linlu Qiu , Fei Sha , Kelsey Allen , Yoon Kim , Tal Linzen , Sjoerd van Steenkiste

Transformer networks are the de facto standard architecture in natural language processing. To date, there are no theoretical analyses of the Transformer's ability to capture tree structures. We focus on the ability of Transformer networks…

Computation and Language · Computer Science 2021-12-23 Qi He , João Sedoc , Jordan Rodu

Many real-world tasks are plagued by limitations on data: in some instances very little data is available and in others, data is protected by privacy enforcing regulations (e.g. GDPR). We consider limitations posed specifically on…

Machine Learning · Computer Science 2022-05-24 Padmanaba Srinivasan , William J. Knottenbelt

Large Language Models demonstrate remarkable mathematical capabilities but at the same time struggle with abstract reasoning and planning. In this study, we explore whether Transformers can learn to abstract and generalize the rules…

Neural and Evolutionary Computing · Computer Science 2024-12-03 Mikhail Burtsev

Increase in data, size, or compute can lead to sudden learning of specific capabilities by a neural network -- a phenomenon often called "emergence''. Beyond scientific understanding, establishing the causal factors underlying such emergent…

Machine Learning · Computer Science 2024-09-10 Ekdeep Singh Lubana , Kyogo Kawaguchi , Robert P. Dick , Hidenori Tanaka

Several recent works demonstrate that transformers can implement algorithms like gradient descent. By a careful construction of weights, these works show that multiple layers of transformers are expressive enough to simulate iterations of…

Machine Learning · Computer Science 2023-11-13 Kwangjun Ahn , Xiang Cheng , Hadi Daneshmand , Suvrit Sra

Much theoretical work has described the ability of transformers to represent formal languages. However, linking theoretical results to empirical performance is not straightforward due to the complex interplay between the architecture, the…

Computation and Language · Computer Science 2024-10-07 Anej Svete , Nadav Borenstein , Mike Zhou , Isabelle Augenstein , Ryan Cotterell

This work studies the class of algorithms for learning with side-information that emerge by extending generative models with embedded context-related variables. Using finite mixture models (FMM) as the prototypical Bayesian network, we show…

Machine Learning · Statistics 2020-08-17 Serafeim Perdikis , Robert Leeb , Ricardo Chavarriaga , José del R. Millán

Transformer has become ubiquitous due to its dominant performance in various NLP and image processing tasks. However, it lacks understanding of how to generate mathematically grounded uncertainty estimates for transformer architectures.…

Computation and Language · Computer Science 2022-06-03 Karthik Abinav Sankararaman , Sinong Wang , Han Fang

Pre-trained language model representations have been successful in a wide range of language understanding tasks. In this paper, we examine different strategies to integrate pre-trained representations into sequence to sequence models and…

Computation and Language · Computer Science 2019-04-02 Sergey Edunov , Alexei Baevski , Michael Auli
‹ Prev 1 3 4 5 6 7 10 Next ›