English
Related papers

Related papers: Stolen Probability: A Structural Weakness of Neura…

200 papers

Continuous-output neural machine translation (CoNMT) replaces the discrete next-word prediction problem with an embedding prediction. The semantic structure of the target embedding space (i.e., closeness of related words) is intuitively…

Computation and Language · Computer Science 2024-04-03 Evgeniia Tokarchuk , Vlad Niculae

Deep learning sequence models have led to a marked increase in performance for a range of Natural Language Processing tasks, but it remains an open question whether they are able to induce proper hierarchical generalizations for…

Computation and Language · Computer Science 2019-06-11 Ethan Wilcox , Roger Levy , Richard Futrell

Distributed representations of words have been shown to capture lexical semantics, as demonstrated by their effectiveness in word similarity and analogical relation tasks. But, these tasks only evaluate lexical semantics indirectly. In this…

Computation and Language · Computer Science 2016-12-02 Thanapon Noraset , Chen Liang , Larry Birnbaum , Doug Downey

Large Language Models (LLMs) have shown promise in clinical applications through prompt engineering, allowing flexible clinical predictions. However, they struggle to produce reliable prediction probabilities, which are crucial for…

Artificial Intelligence · Computer Science 2024-12-05 Bowen Gu , Rishi J. Desai , Kueiyu Joshua Lin , Jie Yang

Embeddings are a basic initial feature extraction step in many machine learning models, particularly in natural language processing. An embedding attempts to map data tokens to a low-dimensional space where similar tokens are mapped to…

Machine Learning · Computer Science 2025-04-10 Golara Ahmadi Azar , Melika Emami , Alyson Fletcher , Sundeep Rangan

By representing words with probability densities rather than point vectors, probabilistic word embeddings can capture rich and interpretable semantic information and uncertainty. The uncertainty information can be particularly meaningful in…

Computation and Language · Computer Science 2018-04-30 Ben Athiwaratkun , Andrew Gordon Wilson

Structured output prediction problems are ubiquitous in machine learning. The prominent approach leverages neural networks as powerful feature extractors, otherwise assuming the independence of the outputs. These outputs, however, jointly…

Autoregressive Large Language Models (LLMs) trained for next-word prediction have demonstrated remarkable proficiency at producing coherent text. But are they equally adept at forming coherent probability judgments? We use probabilistic…

Computation and Language · Computer Science 2025-05-07 Jian-Qiao Zhu , Thomas L. Griffiths

There has been recent interest in whether large language models (LLMs) can introspect about their own internal states. Such abilities would make LLMs more interpretable, and also validate the use of standard introspective methods in…

Computation and Language · Computer Science 2025-09-25 Siyuan Song , Jennifer Hu , Kyle Mahowald

The maximum softmax probability (MSP) represents a default approach when evaluating uncertainty quantification for language model generation with structured output. Although cheap, it is often miscalibrated. Methods that probe the model's…

Machine Learning · Computer Science 2026-05-25 Aliai Eusebi , Alexander Herzog , Xiaoyu Liang , Marie Vasek , Enrico Mariconti , Lorenzo Cavallaro

In this paper, we present a maximum likelihood estimation approach to determine the value vector in transformer models. We model the sequence of value vectors, key vectors, and the query vector as a sequence of Gaussian distributions. The…

Machine Learning · Computer Science 2025-09-17 Jiyong Ma

Language diffusion models aim to improve sampling speed and coherence over autoregressive LLMs. We introduce Neural Flow Diffusion Models for language generation, an extension of NFDM that enables the straightforward application of…

Computation and Language · Computer Science 2026-01-26 Nesta Midavaine , Christian A. Naesseth , Grigory Bartosh

We introduce distributed NLI, a new NLU task with a goal to predict the distribution of human judgements for natural language inference. We show that by applying additional distribution estimation methods, namely, Monte Carlo (MC) Dropout,…

Computation and Language · Computer Science 2022-04-08 Xiang Zhou , Yixin Nie , Mohit Bansal

Some statements have one well-defined continuation (e.g., "the Eiffel Tower is in [Paris]"), whereas others have a natural distribution over multiple options (e.g., "the weighted coin flip was [Heads/Tails].") We argue that language model…

Artificial Intelligence · Computer Science 2025-03-06 Charles Lovering , Michael Krumdick , Viet Dac Lai , Seth Ebner , Nilesh Kumar , Varshini Reddy , Rik Koncel-Kedziorski , Chris Tanner

Deep Metric Learning (DML), a widely-used technique, involves learning a distance metric between pairs of samples. DML uses deep neural architectures to learn semantic embeddings of the input, where the distance between similar examples is…

Machine Learning · Computer Science 2021-02-16 Thomas Kobber Panum , Zi Wang , Pengyu Kan , Earlence Fernandes , Somesh Jha

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

The paper describes a novel approach to Spoken Term Detection (STD) in large spoken archives using deep LSTM networks. The work is based on the previous approach of using Siamese neural networks for STD and naturally extends it to directly…

Computation and Language · Computer Science 2022-10-24 Jan Švec , Luboš Šmídl , Josef V. Psutka , Aleš Pražák

Studying language models (LMs) in terms of well-understood formalisms allows us to precisely characterize their abilities and limitations. Previous work has investigated the representational capacity of recurrent neural network (RNN) LMs in…

Computation and Language · Computer Science 2023-12-20 Anej Svete , Ryan Cotterell

In this study, the output of large language models (LLM) is considered an information source generating an unlimited sequence of symbols drawn from a finite alphabet. Given the probabilistic nature of modern LLMs, we assume a probabilistic…

Computation and Language · Computer Science 2026-02-24 Marco Scharringhausen

Large Language Models (LLMs) have transformed text generation through inherently probabilistic context-aware mechanisms, mimicking human natural language. In this paper, we systematically investigate the performance of various LLMs when…

Computation and Language · Computer Science 2025-02-28 Javier Coronado-Blázquez