English
Related papers

Related papers: Understanding the Emergence of Seemingly Useless F…

200 papers

Predictive learning has emerged as a central paradigm for training models across diverse data domains and is increasingly viewed as a foundation for modern artificial intelligence. A common intuition for this success is that accurate…

Machine Learning · Computer Science 2026-05-06 Aviv Ratzon , Omri Barak

The emergence of large-scale pretrained language models has posed unprecedented challenges in deriving explanations of why the model has made some predictions. Stemmed from the compositional nature of languages, spurious correlations have…

Computation and Language · Computer Science 2023-05-04 Ruochen Zhao , Shafiq Joty , Yongjie Wang , Tan Wang

There have been many recent investigations into prompt-based training of transformer language models for new text genres in low-resource settings. The prompt-based training approach has been found to be effective in generalizing pre-trained…

Computation and Language · Computer Science 2023-06-13 Jennifer D'Souza , Moussab Hrou , Sören Auer

Supervised machine learning models often associate irrelevant nuisance factors with the prediction target, which hurts generalization. We propose a framework for training robust neural networks that induces invariance to nuisances through…

Machine Learning · Computer Science 2019-12-03 Ayush Jaiswal , Rob Brekelmans , Daniel Moyer , Greg Ver Steeg , Wael AbdAlmageed , Premkumar Natarajan

Recurrent Neural Network, Long Short-Term Memory, and Transformer have made great progress in predicting the trajectories of moving objects. Although the trajectory element with the surrounding scene features has been merged to improve…

Computer Vision and Pattern Recognition · Computer Science 2023-04-18 Wendong Zhang , Qingjie Chai , Quanqi Zhang , Chengwei Wu

Categorization is a core component of human linguistic competence. We investigate how a transformer-based language model (LM) learns linguistic categories by comparing its behaviour over the course of training to behaviours which…

Computation and Language · Computer Science 2026-03-19 Jasper Jian , Christopher D. Manning

Although it is known that transformer language models (LMs) pass features from early layers to later layers, it is not well understood how this information is represented and routed by the model. We analyze a mechanism used in two LMs to…

Computation and Language · Computer Science 2025-05-12 Jack Merullo , Carsten Eickhoff , Ellie Pavlick

To improve the explainability of leading Transformer networks used in NLP, it is important to tease apart genuine symbolic rules from merely associative input-output patterns. However, we identify several inconsistencies in how…

Machine Learning · Computer Science 2023-03-02 Tommi Gröndahl , Yujia Guo , N. Asokan

Deployed real-world machine learning applications are often subject to uncontrolled and even potentially malicious inputs. Those out-of-domain inputs can lead to unpredictable outputs and sometimes catastrophic safety issues. Prior studies…

Computation and Language · Computer Science 2022-05-23 Keyang Xu , Tongzheng Ren , Shikun Zhang , Yihao Feng , Caiming Xiong

Next-token prediction (NTP) over large text corpora has become the go-to paradigm to train large language models. Yet, it remains unclear how NTP influences the mapping of linguistic patterns to geometric properties of the resulting model…

Computation and Language · Computer Science 2025-02-20 Yize Zhao , Tina Behnia , Vala Vakilian , Christos Thrampoulidis

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

Machine learning is a data-driven field, and the quality of the underlying datasets plays a crucial role in learning success. However, high performance on held-out test data does not necessarily indicate that a model generalizes or learns…

Computer Vision and Pattern Recognition · Computer Science 2023-05-24 Nicolas M. Müller , Jochen Jacobs , Jennifer Williams , Konstantin Böttinger

Neural sequence models, especially transformers, exhibit a remarkable capacity for in-context learning. They can construct new predictors from sequences of labeled examples $(x, f(x))$ presented in the input without further parameter…

Machine Learning · Computer Science 2023-05-19 Ekin Akyürek , Dale Schuurmans , Jacob Andreas , Tengyu Ma , Denny Zhou

Large-scale transformer-based language models (LMs) demonstrate impressive capabilities in open text generation. However, controlling the generated text's properties such as the topic, style, and sentiment is challenging and often requires…

Computation and Language · Computer Science 2021-03-12 Rohola Zandie , Mohammad H. Mahoor

Large language models (LLMs) contain substantial factual knowledge which is commonly elicited by multiple-choice question-answering prompts. Internally, such models process the prompt through multiple transformer layers, building varying…

Computation and Language · Computer Science 2025-01-31 Didier Chételat , Joseph Cotnareanu , Rylee Thompson , Yingxue Zhang , Mark Coates

Despite the widespread success of Transformers on NLP tasks, recent works have found that they struggle to model several formal languages when compared to recurrent models. This raises the question of why Transformers perform well in…

Machine Learning · Computer Science 2023-07-11 Satwik Bhattamishra , Arkil Patel , Varun Kanade , Phil Blunsom

Transformer-based language models create hidden representations of their inputs at every layer, but only use final-layer representations for prediction. This obscures the internal decision-making process of the model and the utility of its…

Computation and Language · Computer Science 2024-06-21 Alexander Yom Din , Taelin Karidi , Leshem Choshen , Mor Geva

We propose a new architectural change, and post-training pipeline, for making LLMs more verbose reasoners by teaching a model to truncate forward passes early. We augment an existing transformer architecture with an early-exit mechanism at…

Artificial Intelligence · Computer Science 2026-03-25 Elizabeth Pavlova , Mariia Koroliuk , Karthik Viswanathan , Cameron Tice , Edward James Young , Puria Radmard

Whether Large Language Models (LLMs) develop coherent internal world models remains a core debate. While conventional Next-Token Prediction (NTP) focuses on one-step-ahead supervision, Multi-Token Prediction (MTP) has shown promise in…

Machine Learning · Computer Science 2026-04-21 Qimin Zhong , Hao Liao , Haiming Qin , Mingyang Zhou , Rui Mao , Wei Chen , Naipeng Chao

This paper seeks to develop a deeper understanding of the fundamental properties of neural text generations models. The study of artifacts that emerge in machine generated text as a result of modeling choices is a nascent research area.…

Computation and Language · Computer Science 2020-04-15 Yi Tay , Dara Bahri , Che Zheng , Clifford Brunk , Donald Metzler , Andrew Tomkins