English
Related papers

Related papers: Do language models plan ahead for future tokens?

200 papers

Lexical semantics and cognitive science point to affordances (i.e. the actions that objects support) as critical for understanding and representing nouns and verbs. However, study of these semantic features has not yet been integrated with…

Computation and Language · Computer Science 2022-07-07 Jack Merullo , Dylan Ebert , Carsten Eickhoff , Ellie Pavlick

Quantitative and numerical comprehension in language is an important task in many fields like education and finance, but still remains a challenging task for language models. While tool and calculator usage has shown to be helpful to…

Computation and Language · Computer Science 2024-06-27 Vishruth Veerendranath , Vishwa Shah , Kshitish Ghate

Cross-lingual alignment in pretrained language models enables knowledge transfer across languages. Similar alignment has been reported in Whisper-style speech encoders, based on spoken translation retrieval using representational…

Computation and Language · Computer Science 2026-04-07 Ryan Soh-Eun Shim , Domenico De Cristofaro , Chengzhi Martin Hu , Alessandro Vietti , Barbara Plank

A language model's ability to reflect on its own reasoning provides a key advantage for solving complex problems. While most recent research has focused on how this ability develops during reinforcement learning, we show that it actually…

Model diffing is the study of how fine-tuning changes a model's representations and internal algorithms. Many behaviors of interest are introduced during fine-tuning, and model diffing offers a promising lens to interpret such behaviors.…

Machine Learning · Computer Science 2026-02-23 Julian Minder , Clément Dumas , Caden Juang , Bilal Chugtai , Neel Nanda

Pre-trained Transformers are challenging human performances in many NLP tasks. The massive datasets used for pre-training seem to be the key to their success on existing tasks. In this paper, we explore how a range of pre-trained Natural…

While next-token prediction (NTP) has been the standard objective for training language models, it often struggles to capture global structure in reasoning tasks. Multi-token prediction (MTP) has recently emerged as a promising alternative,…

Machine Learning · Computer Science 2026-04-15 Jianhao Huang , Zhanpeng Zhou , Renqiu Xia , Baharan Mirzasoleiman , Weijie Su , Wei Huang

The use of positional embeddings in transformer language models is widely accepted. However, recent research has called into question the necessity of such embeddings. We further extend this inquiry by demonstrating that a randomly…

Computation and Language · Computer Science 2023-05-24 Ta-Chung Chi , Ting-Han Fan , Li-Wei Chen , Alexander I. Rudnicky , Peter J. Ramadge

When pre-trained on large unsupervised textual corpora, language models are able to store and retrieve factual knowledge to some extent, making it possible to use them directly for zero-shot cloze-style question answering. However, storing…

Computation and Language · Computer Science 2020-05-12 Fabio Petroni , Patrick Lewis , Aleksandra Piktus , Tim Rocktäschel , Yuxiang Wu , Alexander H. Miller , Sebastian Riedel

Pre-training has been a popular learning paradigm in deep learning era, especially in annotation-insufficient scenario. Better ImageNet pre-trained models have been demonstrated, from the perspective of architecture, by previous research to…

Computer Vision and Pattern Recognition · Computer Science 2023-08-21 Andong Deng , Xingjian Li , Di Hu , Tianyang Wang , Haoyi Xiong , Chengzhong Xu

This paper aims to improve the performance of large language models by addressing the variable computational demands in inference steps, where some tokens require more computational resources than others. We present HARP, a simple…

Computation and Language · Computer Science 2025-05-27 Romain Storaï , Seung-won Hwang

We introduce a linguistically enhanced combination of pre-training methods for transformers. The pre-training objectives include POS-tagging, synset prediction based on semantic knowledge graphs, and parent prediction based on dependency…

Computation and Language · Computer Science 2023-01-02 Maren Pielka , Svetlana Schmidt , Lisa Pucknat , Rafet Sifa

Large language models exhibit impressive cross-lingual capabilities. However, prior work analyzes this phenomenon through isolated factors and at sparse points during training, limiting our understanding of how cross-lingual generalization…

Computation and Language · Computer Science 2026-04-21 Felicia Körner , Maria Matveev , Florian Eichin , Gitta Kutyniok , Barbara Plank , Michael A. Hedderich

In this paper, we consider the supervised pre-trained transformer for a class of sequential decision-making problems. The class of considered problems is a subset of the general formulation of reinforcement learning in that there is no…

Machine Learning · Computer Science 2024-10-03 Hanzhao Wang , Yu Pan , Fupeng Sun , Shang Liu , Kalyan Talluri , Guanting Chen , Xiaocheng Li

The growth of global consumption has motivated important applications of deep learning to smart manufacturing and machine health monitoring. In particular, analyzing vibration data offers great potential to extract meaningful insights into…

Machine Learning · Computer Science 2024-05-30 Anthony Zhou , Amir Barati Farimani

Large language models (LLMs) sometimes fail to respond appropriately to deterministic tasks -- such as counting or forming acronyms -- because the implicit prior distribution they have learned over sequences of tokens influences their…

Computation and Language · Computer Science 2025-04-18 Liyi Zhang , Veniamin Veselovsky , R. Thomas McCoy , Thomas L. Griffiths

Contextual predictability shapes how we choose and encode words in production. The effects of a word's predictability given preceding or past context are generally well-understood in both production and comprehension, but studies of…

Computation and Language · Computer Science 2026-04-24 Shiva Upadhye , Richard Futrell

This study investigates the layerwise importance of feed-forward networks (FFNs) in Transformer-based language models during pretraining. We introduce an experimental approach that, while maintaining the total parameter count, increases the…

Computation and Language · Computer Science 2025-08-26 Wataru Ikeda , Kazuki Yano , Ryosuke Takahashi , Jaesung Lee , Keigo Shibata , Jun Suzuki

Pre-trained language models (PrLM) have to carefully manage input units when training on a very large text with a vocabulary consisting of millions of words. Previous works have shown that incorporating span-level information over…

Computation and Language · Computer Science 2021-09-16 Rongzhou Bao , Zhuosheng Zhang , Hai Zhao

Large language models (LLMs) have shown potential as tools for scientific discovery. This has engendered growing interest in their use in humanistic disciplines, such as historical linguistics and literary studies. These fields often…

Computation and Language · Computer Science 2026-03-31 Elisabeth Fittschen , Sabrina Li , Tom Lippincott , Leshem Choshen , Craig Messner