English
Related papers

Related papers: Mirostat: A Neural Text Decoding Algorithm that Di…

200 papers

Today's probabilistic language generators fall short when it comes to producing coherent and fluent text despite the fact that the underlying models perform well under standard metrics, e.g., perplexity. This discrepancy has puzzled the…

Computation and Language · Computer Science 2025-06-06 Clara Meister , Tiago Pimentel , Gian Wiher , Ryan Cotterell

Autoregressive language models are trained by minimizing the cross-entropy of the model distribution Q relative to the data distribution P -- that is, minimizing the forward cross-entropy, which is equivalent to maximum likelihood…

Computation and Language · Computer Science 2024-05-28 Shiyue Zhang , Shijie Wu , Ozan Irsoy , Steven Lu , Mohit Bansal , Mark Dredze , David Rosenberg

Conditional text generation often requires lexical constraints, i.e., which words should or shouldn't be included in the output text. While the dominant recipe for conditional text generation has been large-scale pretrained language models…

Computation and Language · Computer Science 2021-04-22 Ximing Lu , Peter West , Rowan Zellers , Ronan Le Bras , Chandra Bhagavatula , Yejin Choi

Standard decoding strategies for text generation, including top-k, nucleus sampling, and contrastive search, select tokens based on likelihood, restricting selection to high-probability regions. Human language production operates…

Computation and Language · Computer Science 2026-03-20 Esteban Garces Arias , Nurzhan Sapargali , Christian Heumann , Matthias Aßenmacher

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

Controllable text generation systems often leverage control codes to direct various properties of the output like style and length. Inspired by recent work on causal inference for NLP, this paper reveals a previously overlooked flaw in…

Computation and Language · Computer Science 2022-10-10 Junyi Chai , Reid Pryzant , Victor Ye Dong , Konstantin Golobokov , Chenguang Zhu , Yi Liu

Deep learning methods have recently achieved great empirical success on machine translation, dialogue response generation, summarization, and other text generation tasks. At a high level, the technique has been to train end-to-end neural…

Computation and Language · Computer Science 2017-11-28 Ziang Xie

Top-$k$ decoding is a widely used method for sampling from LLMs: at each token, only the largest $k$ next-token-probabilities are kept, and the next token is sampled after re-normalizing them to sum to unity. Top-$k$ and other sampling…

Artificial Intelligence · Computer Science 2026-02-24 Georgy Noarov , Soham Mallick , Tao Wang , Sunay Joshi , Yan Sun , Yangxinyu Xie , Mengxin Yu , Edgar Dobriban

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

While large-scale neural language models, such as GPT2 and BART, have achieved impressive results on various text generation tasks, they tend to get stuck in undesirable sentence-level loops with maximization-based decoding algorithms…

Computation and Language · Computer Science 2022-10-11 Jin Xu , Xiaojiang Liu , Jianhao Yan , Deng Cai , Huayang Li , Jian Li

As large-scale language model pretraining pushes the state-of-the-art in text generation, recent work has turned to controlling attributes of the text such models generate. While modifying the pretrained models via fine-tuning remains the…

Computation and Language · Computer Science 2021-08-05 Sachin Kumar , Eric Malmi , Aliaksei Severyn , Yulia Tsvetkov

Self-training (ST) has come to fruition in language understanding tasks by producing pseudo labels, which reduces the labeling bottleneck of language model fine-tuning. Nevertheless, in facilitating semi-supervised controllable language…

Computation and Language · Computer Science 2023-06-21 Yuxi Feng , Xiaoyuan Yi , Laks V. S. Lakshmanan , Xing Xie

Augmenting Large Language Models (LLMs) with retrieved external knowledge has proven effective for improving the factual accuracy of generated responses. Despite their success, retrieval-augmented LLMs still face the distractibility issue,…

Computation and Language · Computer Science 2025-02-18 Zexuan Qiu , Zijing Ou , Bin Wu , Jingjing Li , Aiwei Liu , Irwin King

A mainstream type of current self-supervised learning methods pursues a general-purpose representation that can be well transferred to downstream tasks, typically by optimizing on a given pretext task such as instance discrimination. In…

Computer Vision and Pattern Recognition · Computer Science 2022-10-21 Xin Liu , Zhongdao Wang , Yali Li , Shengjin Wang

Decoding from the output distributions of large language models to produce high-quality text is a complex challenge in language modeling. Various approaches, such as beam search, sampling with temperature, $k-$sampling, nucleus…

Computation and Language · Computer Science 2024-10-22 Esteban Garces Arias , Julian Rodemann , Meimingwei Li , Christian Heumann , Matthias Aßenmacher

Large language models (LM) based on Transformers allow to generate plausible long texts. In this paper, we explore how this generation can be further controlled at decoding time to satisfy certain constraints (e.g. being non-toxic,…

Computation and Language · Computer Science 2022-05-05 Antoine Chaffin , Vincent Claveau , Ewa Kijak

Current language models decode text token by token according to probabilistic distribution, and determining the appropriate candidates for the next token is crucial to ensure generation quality. This study introduces adaptive decoding, a…

Computation and Language · Computer Science 2024-06-04 Wenhong Zhu , Hongkun Hao , Zhiwei He , Yiming Ai , Rui Wang

Large language models achieve strong reasoning performance, yet existing decoding strategies either explore blindly (random sampling) or redundantly (independent multi-sampling). We propose Entropy-Tree, a tree-based decoding method that…

Computation and Language · Computer Science 2026-01-23 Longxuan Wei , Yubo Zhang , Zijiao Zhang , Zhihu Wang , Shiwan Zhao , Tianyu Huang , Huiting Zhao , Chenfei Liu , Shenao Zhang , Junchi Yan

Language models can be prompted to perform a wide variety of zero- and few-shot learning problems. However, performance varies significantly with the choice of prompt, and we do not yet understand why this happens or how to pick the best…

Computation and Language · Computer Science 2024-09-16 Hila Gonen , Srini Iyer , Terra Blevins , Noah A. Smith , Luke Zettlemoyer

Pre-trained Vision-Language (VL) models such as CLIP have demonstrated their excellent performance across numerous downstream tasks. A recent method, Context Optimization (CoOp), further improves the performance of VL models on downstream…

Computation and Language · Computer Science 2024-12-23 Biao Liu , Wenyi Fang , Xiaoyu Wu , Yang Zheng , Zheng Hu , Bo Yuan