English
Related papers

Related papers: Understanding Token Probability Encoding in Output…

200 papers

We introduce a simple modification to the embedding layer. The key change is to infuse token embeddings with information about their spelling. Models trained with these embeddings improve not only on spelling, but also across standard…

Machine Learning · Computer Science 2026-01-27 Markus N. Rabe , Judith Clymo , Zheren Dong

For stochastic models with intractable likelihood functions, approximate Bayesian computation offers a way of approximating the true posterior through repeated comparisons of observations with simulated model outputs in terms of a small set…

Machine Learning · Computer Science 2022-05-24 Carlo Albert , Simone Ulzega , Firat Ozdemir , Fernando Perez-Cruz , Antonietta Mira

Pretrained language models (LMs) are prone to arithmetic errors. Existing work showed limited success in probing numeric values from models' representations, indicating that these errors can be attributed to the inherent unreliability of…

Computation and Language · Computer Science 2025-10-27 Marek Kadlčík , Michal Štefánik , Timothee Mickus , Michal Spiegel , Josef Kuchař

Neural audio codecs, used as speech tokenizers, have demonstrated remarkable potential in the field of speech generation. However, to ensure high-fidelity audio reconstruction, neural audio codecs typically encode audio into long sequences…

Audio and Speech Processing · Electrical Eng. & Systems 2025-06-02 Wenrui Liu , Qian Chen , Wen Wang , Yafeng Chen , Jin Xu , Zhifang Guo , Guanrou Yang , Weiqin Li , Xiaoda Yang , Tao Jin , Minghui Fang , Jialong Zuo , Bai Jionghao , Zemin Liu

Token embeddings play a crucial role in language modeling but, despite this practical relevance, their theoretical understanding remains limited. Our paper addresses the gap by characterizing the structure of embeddings obtained via…

Machine Learning · Computer Science 2025-06-26 Diyuan Wu , Aleksandr Shevchenko , Samet Oymak , Marco Mondelli

Neural language models learn word representations, or embeddings, that capture rich linguistic and conceptual information. Here we investigate the embeddings learned by neural machine translation models, a recently-developed class of neural…

Computation and Language · Computer Science 2015-04-06 Felix Hill , Kyunghyun Cho , Sebastien Jean , Coline Devin , Yoshua Bengio

Understanding what knowledge is implicitly encoded in deep learning models is essential for improving the interpretability of AI systems. This paper examines common methods to explain the knowledge encoded in word embeddings, which are core…

Computation and Language · Computer Science 2025-08-20 Hanna Herasimchyk , Alhassan Abdelhalim , Sören Laue , Michaela Regneri

Modern language models are internally -- and mathematically -- distributions over $\it{token}$ strings rather than $\it{character}$ strings, posing numerous challenges for programmers building user applications on top of them. For example,…

Computation and Language · Computer Science 2025-06-11 Tim Vieira , Ben LeBrun , Mario Giulianelli , Juan Luis Gastaldi , Brian DuSell , John Terilla , Timothy J. O'Donnell , Ryan Cotterell

The likelihood decoder is a stochastic decoder that selects the decoded message at random, using the posterior distribution of the true underlying message given the channel output. In this work, we study a generalized version of this…

Information Theory · Computer Science 2016-11-17 Neri Merhav

Large pre-trained vision-language models have shown great prominence in transferring pre-acquired knowledge to various domains and downstream tasks with appropriate prompting or tuning. Existing prevalent tuning methods can be generally…

Computer Vision and Pattern Recognition · Computer Science 2023-05-31 Huahui Yi , Ziyuan Qin , Wei Xu , Miaotian Guo , Kun Wang , Shaoting Zhang , Kang Li , Qicheng Lao

Large information sizes in samples and features can be encoded to speed up the learning of statistical models based on linear algebra and remove unwanted signals. Encoding information can reduce both sample and feature dimension to a…

Machine Learning · Computer Science 2022-06-23 David Banh , Alan Huang

We present a clustering-based language model using word embeddings for text readability prediction. Presumably, an Euclidean semantic space hypothesis holds true for word embeddings whose training is done by observing word co-occurrences.…

Computation and Language · Computer Science 2017-09-07 Miriam Cha , Youngjune Gwon , H. T. Kung

Embedding models are crucial for tasks in Information Retrieval (IR) and semantic similarity measurement, yet their handling of longer texts and associated positional biases remains underexplored. In this study, we investigate the impact of…

Computation and Language · Computer Science 2026-01-01 Reagan J. Lee , Samarth Goel , Kannan Ramchandran

Language models (LMs) estimate a probability distribution over strings in a natural language; these distributions are crucial for computing perplexity and surprisal in linguistics research. While we are usually concerned with measuring…

Computation and Language · Computer Science 2024-10-15 Tiago Pimentel , Clara Meister

In this work, we introduce a semiparametric token-sequence co-supervision training method. It trains a language model by simultaneously leveraging supervision from the traditional next token prediction loss which is calculated over the…

Computation and Language · Computer Science 2024-03-15 Hyunji Lee , Doyoung Kim , Jihoon Jun , Sejune Joo , Joel Jang , Kyoung-Woon On , Minjoon Seo

We consider probabilistic topic models and more recent word embedding techniques from a perspective of learning hidden semantic representations. Inspired by a striking similarity of the two approaches, we merge them and learn probabilistic…

Computation and Language · Computer Science 2017-11-15 Anna Potapenko , Artem Popov , Konstantin Vorontsov

Weight tying, i.e. sharing parameters between input and output embedding matrices, is common practice in language model design, yet its impact on the learned embedding space remains poorly understood. In this paper, we show that tied…

Computation and Language · Computer Science 2026-03-30 Antonio Lopardo , Avyukth Harish , Catherine Arnett , Akshat Gupta

We study the topmost weight matrix of neural network language models. We show that this matrix constitutes a valid word embedding. When training language models, we recommend tying the input embedding and this output embedding. We analyze…

Computation and Language · Computer Science 2017-02-22 Ofir Press , Lior Wolf

For constructing text embeddings, mean pooling, which averages token embeddings, is the standard approach. This paper examines whether mean pooling actually works well in real models. First, we note that mean pooling can collapse…

Computation and Language · Computer Science 2026-05-01 Tomomasa Hara , Hiroto Kurita , Masaaki Imaizumi , Kentaro Inui , Sho Yokoi

Modern language models are typically trained over subword sequences, but ultimately define probabilities over character-strings. Ideally, the choice of the tokeniser -- which maps character-strings to subwords -- should not affect the…

Computation and Language · Computer Science 2025-06-04 Pietro Lesci , Clara Meister , Thomas Hofmann , Andreas Vlachos , Tiago Pimentel