English
Related papers

Related papers: Momentum Point-Perplexity Mechanics in Large Langu…

200 papers

We seek to understand how the representations of individual tokens and the structure of the learned feature space evolve between layers in deep neural networks under different learning objectives. We focus on the Transformers for our…

Computation and Language · Computer Science 2019-09-05 Elena Voita , Rico Sennrich , Ivan Titov

While large language models (LLMs) excel in mathematical and code reasoning, we observe they struggle with social reasoning tasks, exhibiting cognitive confusion, logical inconsistencies, and conflation between objective world states and…

Computation and Language · Computer Science 2025-10-14 Jialu Du , Guiyang Hou , Yihui Fu , Chen Wu , Wenqi Zhang , Yongliang Shen , Weiming Lu

The rapid advancement of large language models (LLMs) has made machine-generated text increasingly difficult to distinguish from human-written text. While recent studies explore leveraging internal representations of language models to…

Applications · Statistics 2026-05-14 Luxu Liang , Xiang Li

This paper describes the conversion of a Hidden Markov Model into a sequential transducer that closely approximates the behavior of the stochastic model. This transformation is especially advantageous for part-of-speech tagging because the…

cmp-lg · Computer Science 2008-02-03 Andre Kempe

Tracking the internal states of large language models across conversations is important for safety, interpretability, and model welfare, yet current methods are limited. Linear probes and other white-box methods compress high-dimensional…

Artificial Intelligence · Computer Science 2026-04-14 Nicolas Martorell , Bruno Bianchi

Transformers underpin modern large language models (LLMs) and are commonly assumed to be behaviorally unstructured at random initialization, with all meaningful preferences emerging only through large-scale training. We challenge this…

Machine Learning · Statistics 2026-02-06 Siquan Li , Yao Tong , Haonan Wang , Tianyang Hu

Recent reasoning language models, particularly those that employ long latent chains of thought, achieve strong performance on complex agentic tasks. However, as these models operate over increasingly long time horizons, their internal…

Machine Learning · Computer Science 2026-05-27 Hans Peter Lyngsøe Raaschou-Jensen , Constanza Fierro , Anders Søgaard

It has long been established that predictive models can be transformed into lossless compressors and vice versa. Incidentally, in recent years, the machine learning community has focused on training increasingly large and powerful…

Large Language Models (LLMs) exhibit impressive capabilities yet suffer from sensitivity to slight input context variations, hampering reliability. Conventional metrics like accuracy and perplexity fail to assess local prediction…

Computation and Language · Computer Science 2026-02-12 Deyuan Liu , Zecheng Wang , Zhanyue Qin , Zhiying Tu , Dianhui Chu , Dianbo Sui

Large language models (LLMs) tend to verbalize confidence scores that are largely detached from their actual accuracy, yet the geometric relationship governing this behavior remain poorly understood. In this work, we present a mechanistic…

Computation and Language · Computer Science 2026-04-02 Miranda Muqing Miao , Lyle Ungar

The choice of tokenizer can profoundly impact language model performance, yet accessible and reliable evaluations of tokenizer quality remain an open challenge. Inspired by scaling consistency, we show that smaller models can accurately…

Computation and Language · Computer Science 2025-06-04 Jonas F. Lotz , António V. Lopes , Stephan Peitz , Hendra Setiawan , Leonardo Emili

Bidirectional Encoder Representations from Transformers (BERT) reach state-of-the-art results in a variety of Natural Language Processing tasks. However, understanding of their internal functioning is still insufficient and unsatisfactory.…

Computation and Language · Computer Science 2019-09-12 Betty van Aken , Benjamin Winter , Alexander Löser , Felix A. Gers

Augmenting large language models (LLMs) with auxiliary tokens has emerged as a promising strategy for enhancing model performance. In this work, we introduce a lightweight method termed latent tokens; these are dummy tokens that may be…

Machine Learning · Computer Science 2025-05-20 Yuchang Sun , Yanxi Chen , Yaliang Li , Bolin Ding

Can large language models introspect, that is, accurately detect perturbations to their own internal states? We systematically investigate this question using activation steering in Meta-Llama-3.1-8B-Instruct. First, we show that the binary…

Artificial Intelligence · Computer Science 2026-03-03 Ely Hahami , Ishaan Sinha , Lavik Jain , Josh Kaplan , Jon Hahami

Transformer architectures are the backbone of most modern language models, but understanding the inner workings of these models still largely remains an open problem. One way that research in the past has tackled this problem is by…

Computation and Language · Computer Science 2025-02-04 Utkarsh Tiwari , Aviral Gupta , Michael Hahn

We consider the context of molecular motors modelled by a diffusion process driven by the gradient of a weakly periodic potential that depends on an internal degree of freedom. The switch of the internal state, that can freely be…

Probability · Mathematics 2024-02-02 Serena Della Corte , Richard C. Kraaij

Language models (LMs) automatically learn word embeddings during pre-training on language corpora. Although word embeddings are usually interpreted as feature vectors for individual words, their roles in language model generation remain…

Computation and Language · Computer Science 2024-06-07 Chi Han , Jialiang Xu , Manling Li , Yi Fung , Chenkai Sun , Nan Jiang , Tarek Abdelzaher , Heng Ji

Recent advances in interpretability suggest we can project weights and hidden states of transformer-based language models (LMs) to their vocabulary, a transformation that makes them more human interpretable. In this paper, we investigate LM…

Computation and Language · Computer Science 2023-11-27 Shahar Katz , Yonatan Belinkov

Intrinsic self-correction refers to the phenomenon where a language model refines its own outputs purely through prompting, without external feedback or parameter updates. While this approach improves performance across diverse tasks, its…

Computation and Language · Computer Science 2026-02-12 Yu-Ting Lee , Fu-Chieh Chang , Yu-En Shu , Hui-Ying Shih , Pei-Yuan Wu

Translation into morphologically-rich languages challenges neural machine translation (NMT) models with extremely sparse vocabularies where atomic treatment of surface forms is unrealistic. This problem is typically addressed by either…

Computation and Language · Computer Science 2020-02-28 Duygu Ataman , Wilker Aziz , Alexandra Birch
‹ Prev 1 4 5 6 7 8 10 Next ›