English
Related papers

Related papers: Neural Text Generation with Unlikelihood Training

200 papers

Existing curriculum learning approaches to Neural Machine Translation (NMT) require sampling sufficient amounts of "easy" samples from training data at the early training stage. This is not always achievable for low-resource languages where…

Computation and Language · Computer Science 2021-03-23 Chen Liang , Haoming Jiang , Xiaodong Liu , Pengcheng He , Weizhu Chen , Jianfeng Gao , Tuo Zhao

Recent advancements in neural language modelling make it possible to rapidly generate vast amounts of human-sounding text. The capabilities of humans and automatic discriminators to detect machine-generated text have been a large source of…

Computation and Language · Computer Science 2020-05-11 Daphne Ippolito , Daniel Duckworth , Chris Callison-Burch , Douglas Eck

The purpose of unconditional text generation is to train a model with real sentences, then generate novel sentences of the same quality and diversity as the training data. However, when different metrics are used for comparing the methods…

Computation and Language · Computer Science 2020-07-03 Ping Cai , Xingyuan Chen , Peng Jin , Hongjun Wang , Tianrui Li

Recent advances in deep neural language models combined with the capacity of large scale datasets have accelerated the development of natural language generation systems that produce fluent and coherent texts (to various degrees of success)…

Computation and Language · Computer Science 2025-04-15 Cristina Garbacea , Qiaozhu Mei

This work analyses the text memorization behavior of large language models (LLMs) when subjected to nucleus sampling. Stochastic decoding methods like nucleus sampling are typically applied to overcome issues such as monotonous and…

Computation and Language · Computer Science 2024-08-30 Luka Borec , Philipp Sadler , David Schlangen

Recurrent Neural Networks can be trained to produce sequences of tokens given some input, as exemplified by recent results in machine translation and image captioning. The current approach to training them consists of maximizing the…

Machine Learning · Computer Science 2015-09-24 Samy Bengio , Oriol Vinyals , Navdeep Jaitly , Noam Shazeer

A human decision-maker benefits the most from an AI assistant that corrects for their biases. For problems such as generating interpretation of a radiology report given findings, a system predicting only highly likely outcomes may be less…

Computation and Language · Computer Science 2023-06-01 Liyan Tang , Yifan Peng , Yanshan Wang , Ying Ding , Greg Durrett , Justin F. Rousseau

Despite their ubiquity in language generation, it remains unknown why truncation sampling heuristics like nucleus sampling are so effective. We provide a theoretical explanation for the effectiveness of the truncation sampling by proving…

Computation and Language · Computer Science 2023-10-04 Matthew Finlayson , John Hewitt , Alexander Koller , Swabha Swayamdipta , Ashish Sabharwal

Machine translation is a popular test bed for research in neural sequence-to-sequence models but despite much recent research, there is still a lack of understanding of these models. Practitioners report performance degradation with large…

Computation and Language · Computer Science 2018-08-14 Myle Ott , Michael Auli , David Grangier , Marc'Aurelio Ranzato

Large Language Models (LLMs) are increasingly employed in real-world applications, driving the need to evaluate the trustworthiness of their generated text. To this end, reliable uncertainty estimation is essential. Leading uncertainty…

Machine Learning · Computer Science 2026-04-21 Lukas Aichberger , Kajetan Schweighofer , Sepp Hochreiter

Recent advances in language models (LMs) have led to significant improvements in quality on complex NLP tasks, but at the expense of increased inference costs. Cascading offers a simple strategy to achieve more favorable cost-quality…

Computation and Language · Computer Science 2024-04-17 Neha Gupta , Harikrishna Narasimhan , Wittawat Jitkrittum , Ankit Singh Rawat , Aditya Krishna Menon , Sanjiv Kumar

When generating natural language from neural probabilistic models, high probability does not always coincide with high quality: It has often been observed that mode-seeking decoding methods, i.e., those that produce high-probability text…

Computation and Language · Computer Science 2022-04-01 Clara Meister , Gian Wiher , Tiago Pimentel , Ryan Cotterell

Text generation is ubiquitous in many NLP tasks, from summarization, to dialogue and machine translation. The dominant parametric approach is based on locally normalized models which predict one word at a time. While these work remarkably…

Computation and Language · Computer Science 2020-04-27 Yuntian Deng , Anton Bakhtin , Myle Ott , Arthur Szlam , Marc'Aurelio Ranzato

Large Language Models (LLMs) have revolutionised the field of Natural Language Processing (NLP) and have achieved state-of-the-art performance in practically every task in this field. However, the prevalent approach used in text generation,…

Computation and Language · Computer Science 2024-08-12 Nicolo Micheletti , Samuel Belkadi , Lifeng Han , Goran Nenadic

Human and model-generated texts can be distinguished by examining the magnitude of likelihood in language. However, it is becoming increasingly difficult as language model's capabilities of generating human-like texts keep evolving. This…

Computation and Language · Computer Science 2024-10-10 Yang Xu , Yu Wang , Hao An , Zhichen Liu , Yongyuan Li

Neural language models are often trained with maximum likelihood estimation (MLE), where the next word is generated conditioned on the ground-truth word tokens. During testing, however, the model is instead conditioned on previously…

Computation and Language · Computer Science 2020-10-14 Guoyin Wang , Chunyuan Li , Jianqiao Li , Hao Fu , Yuh-Chen Lin , Liqun Chen , Yizhe Zhang , Chenyang Tao , Ruiyi Zhang , Wenlin Wang , Dinghan Shen , Qian Yang , Lawrence Carin

Conditional language models are predominantly trained with maximum likelihood estimation (MLE), giving probability mass to sparsely observed target sequences. While MLE trained models assign high probability to plausible sequences given the…

Computation and Language · Computer Science 2022-10-04 Yao Zhao , Misha Khalman , Rishabh Joshi , Shashi Narayan , Mohammad Saleh , Peter J. Liu

The paradigm of Next Token Prediction (NTP) has driven the unprecedented success of Large Language Models (LLMs), but is also the source of their most persistent weaknesses such as poor long-term planning, error accumulation, and…

Computation and Language · Computer Science 2025-09-30 Charlie Wyatt , Aditya Joshi , Flora Salim

Generating coherent and cohesive long-form texts is a challenging task. Previous works relied on large amounts of human-generated texts to train neural language models. However, few attempted to explicitly improve neural language models…

Computation and Language · Computer Science 2019-05-30 Woon Sang Cho , Pengchuan Zhang , Yizhe Zhang , Xiujun Li , Michel Galley , Chris Brockett , Mengdi Wang , Jianfeng Gao

Modern applications and progress in deep learning research have created renewed interest for generative models of text and of images. However, even today it is unclear what objective functions one should use to train and evaluate these…

Machine Learning · Statistics 2015-11-17 Ferenc Huszár