English
Related papers

Related papers: The Randomness Floor: Measuring Intrinsic Non-Rand…

200 papers

This paper presents a comprehensive evaluation of quantum text generation models against traditional Transformer/MLP architectures, addressing the growing interest in quantum computing applications for natural language processing. We…

Quantum Physics · Physics 2025-09-01 Chi-Sheng Chen , En-Jui Kuo

The increasing prevalence of sparse Mixture-of-Experts (MoE) architectures in large language models raises important questions regarding their reliability under stochastic decoding. While conditional computation enables substantial gains in…

Machine Learning · Computer Science 2026-01-06 Kabir Grover

Prompts play a crucial role in guiding the responses of Large Language Models (LLMs). However, the intricate role of individual tokens in prompts, known as input saliency, in shaping the responses remains largely underexplored. Existing…

Computation and Language · Computer Science 2024-05-21 Zijian Feng , Hanzhang Zhou , Zixiao Zhu , Junlang Qian , Kezhi Mao

The neutral theory of genetic and linguistic evolution holds that the relative frequencies of variants evolve by random drift. Neutral evolution remains a plausible null model of language change. In this paper we provide evidence against…

Physics and Society · Physics 2020-05-18 James Burridge , Tamsin Blaxter

Perplexity (per word) is the most widely used metric for evaluating language models. Despite this, there has been no dearth of criticism for this metric. Most of these criticisms center around lack of correlation with extrinsic metrics like…

Computation and Language · Computer Science 2016-04-01 Kushal Arora , Anand Rangarajan

Many NLP applications, such as biomedical data and technical support, have 10-100 million tokens of in-domain data and limited computational resources for learning from it. How should we train a language model in this scenario? Most…

Computation and Language · Computer Science 2020-10-01 Charles Welch , Rada Mihalcea , Jonathan K. Kummerfeld

Reward guidance, also known as posterior sampling, is a popular method for test-time adaptation and post-training in continuous diffusion models. In this paper, we study reward guidance for discrete diffusion language models; now, one…

Machine Learning · Computer Science 2026-05-14 Atula Tejaswi , Litu Rout , Constantine Caramanis , Sanjay Shakkottai , Sujay Sanghavi

Transformers achieve unrivalled performance in modelling language, but remain inefficient in terms of memory and time complexity. A possible remedy is to reduce the sequence length in the intermediate layers by pooling fixed-length segments…

Computation and Language · Computer Science 2023-10-25 Piotr Nawrot , Jan Chorowski , Adrian Łańcucki , Edoardo M. Ponti

Large Language Models (LLMs) have reshaped natural language processing with their impressive capabilities. However, their ever-increasing size has raised concerns about their effective deployment and the need for LLM compression. This study…

Empirical Mode Decomposition(EMD) is an adaptive data analysis technique for analyzing nonlinear and nonstationary data[1]. EMD decomposes the original data into a number of Intrinsic Mode Functions(IMFs)[1] for giving better physical…

Methodology · Statistics 2016-01-27 Sumit Kumar Ram , Marta Molinas

Since Bahdanau et al. [1] first introduced attention for neural machine translation, most sequence-to-sequence models made use of attention mechanisms [2, 3, 4]. While they produce soft-alignment matrices that could be interpreted as…

Computation and Language · Computer Science 2019-09-12 Marcely Zanon Boito , Aline Villavicencio , Laurent Besacier

In this paper, we investigate the output token probability information in the output embedding of language models. We find an approximate common log-linear encoding of output token probabilities within the output embedding vectors and…

Computation and Language · Computer Science 2024-12-12 Hakaze Cho , Yoshihiro Sakai , Kenshiro Tanaka , Mariko Kato , Naoya Inoue

Large language models are trained and evaluated on quantitative reasoning tasks written in clean, emotionally neutral language. However, real-world queries are often wrapped in frustration, urgency or enthusiasm. Does emotional framing…

Computation and Language · Computer Science 2026-04-10 Atahan Dokme , Benjamin Reichman , Larry Heck

The cognitive mechanisms needed to account for the English past tense have long been a subject of debate in linguistics and cognitive science. Neural network models were proposed early on, but were shown to have clear flaws. Recently,…

Computation and Language · Computer Science 2019-06-05 Maria Corkery , Yevgen Matusevych , Sharon Goldwater

Existing training criteria in automatic speech recognition(ASR) permit the model to freely explore more than one time alignments between the feature and label sequences. In this paper, we use entropy to measure a model's uncertainty, i.e.…

Computation and Language · Computer Science 2022-12-26 Ehsan Variani , Ke Wu , David Rybach , Cyril Allauzen , Michael Riley

In this work, we introduce Entropy Area Score (EAS), a simple yet effective metric to quantify uncertainty in the answer generation process of reasoning large language models (LLMs). EAS requires neither external models nor repeated…

Artificial Intelligence · Computer Science 2025-08-29 Yongfu Zhu , Lin Sun , Guangxiang Zhao , Weihong Lin , Xiangzheng Zhang

Text generation models are notoriously vulnerable to errors in the training data. With the wide-spread availability of massive amounts of web-crawled data becoming more commonplace, how can we enhance the robustness of models trained on a…

Computation and Language · Computer Science 2024-03-20 Tianjian Li , Haoran Xu , Philipp Koehn , Daniel Khashabi , Kenton Murray

The traditional approach to morphological inflection (the task of modifying a base word (lemma) to express grammatical categories) has been, for decades, to consider lexical entries of lemma-tag-form triples uniformly, lacking any…

Computation and Language · Computer Science 2025-10-28 Tomáš Sourada , Jana Straková

Diffusion and flow-based models have become the de facto approaches for generating continuous data, e.g., in domains such as images and videos. Their success has attracted growing interest in applying them to language modeling. Unlike their…

Computation and Language · Computer Science 2026-05-12 Keya Hu , Linlu Qiu , Yiyang Lu , Hanhong Zhao , Tianhong Li , Yoon Kim , Jacob Andreas , Kaiming He

This paper presents TEVR, a speech recognition model designed to minimize the variation in token entropy w.r.t. to the language model. This takes advantage of the fact that if the language model will reliably and accurately predict a token…

Computation and Language · Computer Science 2022-06-28 Hajo Nils Krabbenhöft , Erhardt Barth
‹ Prev 1 3 4 5 6 7 10 Next ›