English
Related papers

Related papers: Weight-based Analysis of Detokenization in Languag…

200 papers

The success of Transformer language models is widely credited to their dot-product attention mechanism, which interweaves a set of key design principles: mixing information across positions (enabling multi-token interactions),…

Computation and Language · Computer Science 2025-10-14 Huiyin Xue , Nafise Sadat Moosavi , Nikolaos Aletras

We investigate the robustness of Large Language Models (LLMs) to structural interventions by deleting and swapping adjacent layers during inference. Surprisingly, models retain 72-95% of their original top-1 prediction accuracy without any…

Machine Learning · Computer Science 2025-06-17 Vedang Lad , Jin Hwa Lee , Wes Gurnee , Max Tegmark

Attention mechanisms are ubiquitous components in neural architectures applied to natural language processing. In addition to yielding gains in predictive accuracy, attention weights are often claimed to confer interpretability, purportedly…

Computation and Language · Computer Science 2020-04-08 Danish Pruthi , Mansi Gupta , Bhuwan Dhingra , Graham Neubig , Zachary C. Lipton

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

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

We study minimal attention-only transformers under all-token corruption and show they admit a two-stage empirical Bayes interpretation. A single attention step computes a kernel-weighted posterior mean with respect to the empirical…

Machine Learning · Computer Science 2026-05-29 Matthew Smart , Soumya Ganguly , Nilava Metya , Alexandre V. Morozov , Anirvan M. Sengupta

Sequence modelling requires determining which past tokens are causally relevant from the context and their importance: a process inherent to the attention layers in transformers, yet whose underlying learned mechanisms remain poorly…

Machine Learning · Computer Science 2026-04-14 Francesco D'Angelo , Nicolas Flammarion

Language and vision-language models have shown impressive performance across a wide range of tasks, but their internal mechanisms remain only partly understood. In this work, we study how individual attention heads in text-generative models…

Computer Vision and Pattern Recognition · Computer Science 2026-01-15 Lorenzo Basile , Valentino Maiorca , Diego Doimo , Francesco Locatello , Alberto Cazzaniga

The Transformer is a fully attention-based alternative to recurrent networks that has achieved state-of-the-art results across a range of NLP tasks. In this paper, we analyze the structure of attention in a Transformer language model, the…

Computation and Language · Computer Science 2019-06-20 Jesse Vig , Yonatan Belinkov

Large language models often reason beyond surface tokens, but the internal stage at which token-level information becomes abstract relational structure remains unclear. We investigate this question by analyzing how attention heads and…

Artificial Intelligence · Computer Science 2026-05-22 Junjie Zhang , Zhen Shen , Xisong Dong , Gang Xiong

Investigating deep learning language models has always been a significant research area due to the ``black box" nature of most advanced models. With the recent advancements in pre-trained language models based on transformers and their…

Computation and Language · Computer Science 2023-06-22 Mohamad Ballout , Ulf Krumnack , Gunther Heidemann , Kai-Uwe Kühnberger

Transformer-based language models are trained on large datasets to predict the next token given an input sequence. Despite this simple training objective, they have led to revolutionary advances in natural language processing. Underlying…

Machine Learning · Computer Science 2024-03-14 Yingcong Li , Yixiao Huang , M. Emrullah Ildiz , Ankit Singh Rawat , Samet Oymak

Can we localize the weights and mechanisms used by a language model to memorize and recite entire paragraphs of its training data? In this paper, we show that while memorization is spread across multiple layers and model components,…

Computation and Language · Computer Science 2024-04-01 Niklas Stoehr , Mitchell Gordon , Chiyuan Zhang , Owen Lewis

Large Vision Language Models show impressive performance across image and video understanding tasks, yet their computational cost grows rapidly with the number of visual tokens. Existing token pruning methods mitigate this issue through…

Computer Vision and Pattern Recognition · Computer Science 2026-04-02 Dong-Jae Lee , Sunghyun Baek , Junmo Kim

Attention mechanisms have recently boosted performance on a range of NLP tasks. Because attention layers explicitly weight input components' representations, it is also often assumed that attention can be used to identify information that…

Computation and Language · Computer Science 2019-06-11 Sofia Serrano , Noah A. Smith

Subword tokenization introduces a computational layer in language models where many distinct token sequences decode to the same surface form and preserve meaning, yet induce different internal computations. Despite this non-uniqueness,…

Computation and Language · Computer Science 2026-01-14 Adrian Cosma , Stefan Ruseti , Emilian Radoi , Mihai Dascalu

Large language models (LLMs) have demonstrated strong performance on a variety of natural language processing (NLP) tasks. However, they often struggle with long-text sequences due to the ``lost in the middle'' phenomenon. This issue has…

Computation and Language · Computer Science 2025-12-16 Zewen Qiang , Sendong Zhao , Haochun Wang , Bing Qin , Ting Liu

The attention mechanism lies at the core of the transformer architecture, providing an interpretable model-internal signal that has motivated a growing interest in attention-based model explanations. Although attention weights do not…

Machine Learning · Computer Science 2025-08-13 Marte Eggen , Jacob Lysnæs-Larsen , Inga Strümke

Token representation strategies within large-scale neural architectures often rely on contextually refined embeddings, yet conventional approaches seldom encode structured relationships explicitly within token interactions. Self-attention…

Computation and Language · Computer Science 2025-03-27 James Blades , Frederick Somerfield , William Langley , Susan Everingham , Maurice Witherington

Attention mechanism plays a dominant role in the sequence generation models and has been used to improve the performance of machine translation and abstractive text summarization. Different from neural machine translation, in the task of…

Computation and Language · Computer Science 2020-04-09 Piji Li , Lidong Bing , Zhongyu Wei , Wai Lam
‹ Prev 1 2 3 10 Next ›