English
Related papers

Related papers: DiffSampling: Enhancing Diversity and Accuracy in …

200 papers

As text generation has become a core capability of modern Large Language Models (LLMs), it underpins a wide range of downstream applications. However, most existing LLMs rely on autoregressive (AR) generation, producing one token at a time…

Computation and Language · Computer Science 2026-02-11 Lingzhe Zhang , Liancheng Fang , Chiming Duan , Minghua He , Leyi Pan , Pei Xiao , Shiyu Huang , Yunpeng Zhai , Xuming Hu , Philip S. Yu , Aiwei Liu

Current state-of-the-art text generators build on powerful language models such as GPT-2, achieving impressive performance. However, to avoid degenerate text, they require sampling from a modified softmax, via temperature parameters or…

Computation and Language · Computer Science 2020-10-06 Pedro Henrique Martins , Zita Marinho , André F. T. Martins

Neural networks struggle with image classification when biases are learned and misleads correlations, affecting their generalization and performance. Previous methods require attribute labels (e.g. background, color) or utilizes Generative…

Computer Vision and Pattern Recognition · Computer Science 2024-11-26 Donggeun Ko , Dongjun Lee , Namjun Park , Wonkyeong Shim , Jaekwang Kim

Disentangling the encodings of neural models is a fundamental aspect for improving interpretability, semantic control and downstream task performance in Natural Language Processing. Currently, most disentanglement methods are unsupervised…

Computation and Language · Computer Science 2023-02-17 Danilo S. Carvalho , Giangiacomo Mercatali , Yingji Zhang , Andre Freitas

The autoregressive decoding for text generation in large language models (LLMs), while widely used, is inherently suboptimal due to the lack of a built-in mechanism to perform refinement and/or correction of the generated content. In this…

Computation and Language · Computer Science 2025-06-03 Zeyu Tang , Zhenhao Chen , Xiangchen Song , Loka Li , Yunlong Deng , Yifan Shen , Guangyi Chen , Peter Spirtes , Kun Zhang

Despite some empirical success at correcting exposure bias in machine translation, scheduled sampling algorithms suffer from a major drawback: they incorrectly assume that words in the reference translations and in sampled sequences are…

Computation and Language · Computer Science 2019-05-07 Weijia Xu , Xing Niu , Marine Carpuat

Language models generate texts by successively predicting probability distributions for next tokens given past ones. A growing field of interest tries to leverage external information in the decoding process so that the generated texts have…

Computation and Language · Computer Science 2022-04-26 Antoine Chaffin , Thomas Scialom , Sylvain Lamprier , Jacopo Staiano , Benjamin Piwowarski , Ewa Kijak , Vincent Claveau

Generic generation and manipulation of text is challenging and has limited success compared to recent deep generative modeling in visual domain. This paper aims at generating plausible natural language sentences, whose attributes are…

Machine Learning · Computer Science 2018-09-14 Zhiting Hu , Zichao Yang , Xiaodan Liang , Ruslan Salakhutdinov , Eric P. Xing

A latent-variable model is introduced for text matching, inferring sentence representations by jointly optimizing generative and discriminative objectives. To alleviate typical optimization challenges in latent-variable models for text, we…

Computation and Language · Computer Science 2017-11-23 Dinghan Shen , Yizhe Zhang , Ricardo Henao , Qinliang Su , Lawrence Carin

Consistency in the output of language models is critical for their reliability and practical utility. Due to their training objective, language models learn to model the full space of possible continuations, leading to outputs that can vary…

Computation and Language · Computer Science 2025-03-04 Damien de Mijolla , Hannan Saddiq , Kim Moore

We propose a new model for multi-token prediction in transformers, aiming to enhance sampling efficiency without compromising accuracy. Motivated by recent work that predicts the probabilities of subsequent tokens using multiple heads, we…

Machine Learning · Computer Science 2025-02-11 Artem Basharin , Andrei Chertkov , Ivan Oseledets

Stochastic sampling strategies such as top-k and top-p have been widely used in dialogue generation task. However, as an open-domain chatting system, there will be two different conversation scenarios, i.e. chit-chat and knowledge-based…

Computation and Language · Computer Science 2024-06-13 Yiwei Li , Fei Mi , Yitong Li , Yasheng Wang , Bin Sun , Shaoxiong Feng , Kan Li

This work studies discrete diffusion probabilistic models with applications to natural language generation. We derive an alternative yet equivalent formulation of the sampling from discrete diffusion processes and leverage this insight to…

Computation and Language · Computer Science 2024-08-05 Lin Zheng , Jianbo Yuan , Lei Yu , Lingpeng Kong

Probabilistic programming languages rely fundamentally on some notion of sampling, and this is doubly true for probabilistic programming languages which perform Bayesian inference using Monte Carlo techniques. Verifying samplers - proving…

Programming Languages · Computer Science 2023-04-27 Fredrik Dahlqvist , Alexandra Silva , William Smith

Natural language counterfactual generation aims to minimally modify a given text such that the modified text will be classified into a different class. The generated counterfactuals provide insight into the reasoning behind a model's…

Computation and Language · Computer Science 2024-10-08 Yongjie Wang , Xiaoqi Qiu , Yu Yue , Xu Guo , Zhiwei Zeng , Yuhong Feng , Zhiqi Shen

As the basis of generative AI, an autoregressive model requires the generation of a new token depending on all the previously generated tokens, which brings high quality but also restricts the model to generate tokens one by one, forming a…

Computation and Language · Computer Science 2025-07-02 Zixian Huang , Chenxu Niu , Yu Gu , Gengyang Xiao , Xinwei Huang , Gong Cheng

Recently, there has been a surge in the use of generated data to enhance the performance of downstream models, largely due to the advancements in pre-trained language models. However, most prevailing methods trained generative and…

Computation and Language · Computer Science 2023-09-26 Tong Wu , Hao Wang , Zhongshen Zeng , Wei Wang , Hai-Tao Zheng , Jiaxing Zhang

A critical component of a successful language generation pipeline is the decoding algorithm. However, the general principles that should guide the choice of a decoding algorithm remain unclear. Previous works only compare decoding…

Can continuous diffusion models bring the same performance breakthrough on natural language they did for image generation? To circumvent the discrete nature of text data, we can simply project tokens in a continuous space of embeddings, as…

Generating diverse responses is crucial for test-time scaling of large language models (LLMs), yet standard stochastic sampling mostly yields surface-level lexical variation, limiting semantic exploration. In this paper, we propose…

Computation and Language · Computer Science 2026-04-29 Yuanhao Zeng , Ao Lu , Lufei Li , Zheng Zhang , Yexin Li , Kan Ren
‹ Prev 1 3 4 5 6 7 10 Next ›