English
Related papers

Related papers: Perturbation is All You Need for Extrapolating Lan…

200 papers

While there is much recent interest in studying why Transformer-based large language models make predictions the way they do, the complex computations performed within each layer have made their behavior somewhat opaque. To mitigate this…

Computation and Language · Computer Science 2023-06-06 Byung-Doh Oh , William Schuler

This paper presents Diffusion Forcing, a new training paradigm where a diffusion model is trained to denoise a set of tokens with independent per-token noise levels. We apply Diffusion Forcing to sequence generative modeling by training a…

Machine Learning · Computer Science 2024-12-11 Boyuan Chen , Diego Marti Monso , Yilun Du , Max Simchowitz , Russ Tedrake , Vincent Sitzmann

Large language models show strong performance on knowledge intensive tasks such as fact-checking and question answering, yet they often struggle with numerical reasoning. We present a systematic evaluation of state-of-the-art models for…

Computation and Language · Computer Science 2025-11-14 Peter Røysland Aarnes , Vinay Setty

Predicting upcoming events is critical to our ability to interact with our environment. Transformer models, trained on next-word prediction, appear to construct representations of linguistic input that can support diverse downstream tasks.…

Computation and Language · Computer Science 2023-11-10 Eghbal A. Hosseini , Evelina Fedorenko

Extrapolation -- the ability to make inferences that go beyond the scope of one's experiences -- is a hallmark of human intelligence. By contrast, the generalization exhibited by contemporary neural network algorithms is largely limited to…

Computer Vision and Pattern Recognition · Computer Science 2023-09-08 Taylor W. Webb , Zachary Dulberg , Steven M. Frankland , Alexander A. Petrov , Randall C. O'Reilly , Jonathan D. Cohen

The ability to extrapolate, i.e., to make predictions on sequences that are longer than those presented as training examples, is a challenging problem for current deep learning models. Recent work shows that this limitation persists in…

Computation and Language · Computer Science 2022-11-29 Mirelle Bueno , Carlos Gemmell , Jeffrey Dalton , Roberto Lotufo , Rodrigo Nogueira

Why do modern language models, trained to do well on next-word prediction, appear to generate coherent documents and capture long-range structure? Here we show that next-token prediction is provably powerful for learning longer-range…

Machine Learning · Computer Science 2025-12-09 Xinyuan Cao , Santosh S. Vempala

Despite the tremendous success of deep neural networks in various learning problems, it has been observed that adding an intentionally designed adversarial perturbation to inputs of these architectures leads to erroneous classification with…

Machine Learning · Computer Science 2018-12-19 Emilio Rafael Balda , Arash Behboodi , Rudolf Mathar

Providing technologies to communities or domains where training data is scarce or protected e.g., for privacy reasons, is becoming increasingly important. To that end, we generalise methods for unsupervised transfer from multiple input…

Computation and Language · Computer Science 2021-10-11 Kemal Kurniawan , Lea Frermann , Philip Schulz , Trevor Cohn

We propose a simple data augmentation protocol aimed at providing a compositional inductive bias in conditional and unconditional sequence models. Under this protocol, synthetic training examples are constructed by taking real training…

Computation and Language · Computer Science 2020-05-20 Jacob Andreas

Pre-trained language models have been successful on text classification tasks, but are prone to learning spurious correlations from biased datasets, and are thus vulnerable when making inferences in a new domain. Prior work reveals such…

Computation and Language · Computer Science 2022-01-03 Huihan Yao , Ying Chen , Qinyuan Ye , Xisen Jin , Xiang Ren

We investigate the extent to which modern, neural language models are susceptible to structural priming, the phenomenon whereby the structure of a sentence makes the same structure more probable in a follow-up sentence. We explore how…

Computation and Language · Computer Science 2022-06-30 Arabella Sinclair , Jaap Jumelet , Willem Zuidema , Raquel Fernández

Prompts have been shown to be an effective method to adapt a frozen Pretrained Language Model (PLM) to perform well on downstream tasks. Prompts can be represented by a human-engineered word sequence or by a learned continuous embedding. In…

Computation and Language · Computer Science 2023-07-06 Jonathan Pilault , Can Liu , Mohit Bansal , Markus Dreyer

Large language models are versatile tools but are not suitable for small inference budgets. Small models have more efficient inference, but their lower capacity means that their performance can be good only if one limits their scope to a…

Machine Learning · Computer Science 2024-11-01 David Grangier , Angelos Katharopoulos , Pierre Ablin , Awni Hannun

Multi-step ahead prediction in language models is challenging due to the discrepancy between training and test time processes. At test time, a sequence predictor is required to make predictions given past predictions as the input, instead…

Computation and Language · Computer Science 2021-01-26 James O' Neill , Danushka Bollegala

Autoregressive decoding in language models is inherently slow, generating only one token per forward pass. We propose Parallel Token Prediction (PTP), a general-purpose framework for predicting multiple tokens in a single model call. PTP…

Computation and Language · Computer Science 2026-03-06 Felix Draxler , Justus Will , Farrin Marouf Sofian , Theofanis Karaletsos , Sameer Singh , Stephan Mandt

Transformer language models are state of the art in a multitude of NLP tasks. Despite these successes, their opaqueness remains problematic. Recent methods aiming to provide interpretability and explainability to black-box models primarily…

Computation and Language · Computer Science 2022-03-14 Felix Friedrich , Patrick Schramowski , Christopher Tauchmann , Kristian Kersting

Language model-based instruction-following systems have lately shown increasing performance on many benchmark tasks, demonstrating the capability of adapting to a broad variety of instructions. However, such systems are often not designed…

Computation and Language · Computer Science 2024-03-20 Rahul Nadkarni , Yizhong Wang , Noah A. Smith

Large NLP models have recently shown impressive performance in language understanding tasks, typically evaluated by their fine-tuned performance. Alternatively, probing has received increasing attention as being a lightweight method for…

Computation and Language · Computer Science 2022-10-17 Zining Zhu , Soroosh Shahtalebi , Frank Rudzicz

Recent neural supervised topic segmentation models achieve distinguished superior effectiveness over unsupervised methods, with the availability of large-scale training corpora sampled from Wikipedia. These models may, however, suffer from…

Computation and Language · Computer Science 2022-09-20 Linzi Xing , Patrick Huber , Giuseppe Carenini