English
Related papers

Related papers: Truncation Sampling as Language Model Desmoothing

200 papers

The ability to cheaply train text classifiers is critical to their use in information retrieval, content analysis, natural language processing, and other tasks involving data which is partly or fully textual. An algorithm for sequential…

cmp-lg · Computer Science 2008-02-03 David D. Lewis , William A. Gale

Large denoising diffusion models, such as Stable Diffusion, have been trained on billions of image-caption pairs to perform text-conditioned image generation. As a byproduct of this training, these models have acquired general knowledge…

Computer Vision and Pattern Recognition · Computer Science 2025-10-07 Alexandros Graikos , Nebojsa Jojic , Dimitris Samaras

Stopwords carry little semantic information and are often removed from text data to reduce dataset size and improve machine learning model performance. Consequently, researchers have sought to develop techniques for generating effective…

Computation and Language · Computer Science 2022-09-07 Daniel M. DiPietro

Text summarization is a fundamental task in natural language processing (NLP), and the information explosion has made long-document processing increasingly demanding, making summarization essential. Existing research mainly focuses on model…

An algorithm is proposed, analyzed, and tested for solving continuous nonlinear-equality-constrained optimization problems where the objective and constraint functions are defined by expectations or averages over large, finite numbers of…

Optimization and Control · Mathematics 2026-05-14 Frank E. Curtis , Lingjun Guo , Daniel P. Robinson

In this study, we propose a simple and effective preprocessing method for subword segmentation based on a data compression algorithm. Compression-based subword segmentation has recently attracted significant attention as a preprocessing…

Computation and Language · Computer Science 2023-03-02 Keita Nonaka , Kazutaka Yamanouchi , Tomohiro I , Tsuyoshi Okita , Kazutaka Shimada , Hiroshi Sakamoto

Recently, Large Language Models (LLMs) have demonstrated outstanding performance across a wide range of downstream language tasks. Temperature sampling is a commonly used decoding strategy for LLMs' generation process. However, a fixed…

Computation and Language · Computer Science 2024-04-04 Shimao Zhang , Yu Bao , Shujian Huang

Autoregressive language models, pretrained using large text corpora to do well on next word prediction, have been successful at solving many downstream tasks, even with zero-shot usage. However, there is little theoretical understanding of…

Computation and Language · Computer Science 2021-04-15 Nikunj Saunshi , Sadhika Malladi , Sanjeev Arora

Sample selection is a straightforward technique to combat noisy labels, aiming to prevent mislabeled samples from degrading the robustness of neural networks. However, existing methods mitigate compounding selection bias either by…

Computer Vision and Pattern Recognition · Computer Science 2026-01-16 Kangye Ji , Fei Cheng , Zeqing Wang , Qichang Zhang , Bohu Huang

Thompson sampling has emerged as an effective heuristic for a broad range of online decision problems. In its basic form, the algorithm requires computing and sampling from a posterior distribution over models, which is tractable only for…

Machine Learning · Statistics 2023-04-26 Xiuyuan Lu , Benjamin Van Roy

This paper addresses a fundamental problem in random variate generation: given access to a random source that emits a stream of independent fair bits, what is the most accurate and entropy-efficient algorithm for sampling from a discrete…

Data Structures and Algorithms · Computer Science 2020-03-10 Feras A. Saad , Cameron E. Freer , Martin C. Rinard , Vikash K. Mansinghka

We present a setup for training, evaluating and interpreting neural language models, that uses artificial, language-like data. The data is generated using a massive probabilistic grammar (based on state-split PCFGs), that is itself derived…

Computation and Language · Computer Science 2023-10-24 Jaap Jumelet , Willem Zuidema

Speculative decoding accelerates inference for Large Language Models by using a lightweight draft model to propose candidate tokens that are verified in parallel by a larger target model. Prior work shows that the draft model often…

Computation and Language · Computer Science 2026-03-06 Ofir Ben Shoham

Fine-tuning large language models (LLMs) is intended to improve their reasoning capabilities, yet we uncover a counterintuitive effect: models often forget how to solve problems they previously answered correctly during training. We term…

Artificial Intelligence · Computer Science 2025-05-27 Yuetai Li , Zhangchen Xu , Fengqing Jiang , Bhaskar Ramasubramanian , Luyao Niu , Bill Yuchen Lin , Xiang Yue , Radha Poovendran

Topic segmentation is critical for obtaining structured documents and improving downstream tasks such as information retrieval. Due to its ability of automatically exploring clues of topic shift from abundant labeled data, recent supervised…

Computation and Language · Computer Science 2023-10-24 Hai Yu , Chong Deng , Qinglin Zhang , Jiaqing Liu , Qian Chen , Wen Wang

Automatic segmentation of text into minimal content-bearing units is an unsolved problem even for languages like English. Spaces between words offer an easy first approximation, but this approximation is not good enough for machine…

cmp-lg · Computer Science 2008-02-03 I. Dan Melamed

In streaming settings, speech recognition models have to map sub-sequences of speech to text before the full audio stream becomes available. However, since alignment information between speech and text is rarely available during training,…

Audio and Speech Processing · Electrical Eng. & Systems 2023-12-20 Oscar Chang , Dongseong Hwang , Olivier Siohan

Extracting and identifying latent topics in large text corpora has gained increasing importance in Natural Language Processing (NLP). Most models, whether probabilistic models similar to Latent Dirichlet Allocation (LDA) or neural topic…

Computation and Language · Computer Science 2023-03-31 Anton Thielmann , Quentin Seifert , Arik Reuter , Elisabeth Bergherr , Benjamin Säfken

Scheduled sampling is a technique for avoiding one of the known problems in sequence-to-sequence generation: exposure bias. It consists of feeding the model a mix of the teacher forced embeddings and the model predictions from the previous…

Computation and Language · Computer Science 2019-06-28 Tsvetomila Mihaylova , André F. T. Martins

Assisted by the availability of data and high performance computing, deep learning techniques have achieved breakthroughs and surpassed human performance empirically in difficult tasks, including object recognition, speech recognition, and…

Machine Learning · Computer Science 2019-01-23 Shaeke Salman , Xiuwen Liu