English
Related papers

Related papers: The Truncation Blind Spot: How Decoding Strategies…

200 papers

Long samples of text from neural language models can be of poor quality. Truncation sampling algorithms--like top-$p$ or top-$k$ -- address this by setting some words' probabilities to zero at each step. This work provides framing for the…

Computation and Language · Computer Science 2022-10-28 John Hewitt , Christopher D. Manning , Percy Liang

Recent improvements in the quality of the generations by large language models have spurred research into identifying machine-generated text. Such work often presents high-performing detectors. However, humans and machines can produce text…

Computation and Language · Computer Science 2024-12-13 Jad Doughman , Osama Mohammed Afzal , Hawau Olamide Toyin , Shady Shehata , Preslav Nakov , Zeerak Talat

Generative Language Models rely on autoregressive decoding to produce the output sequence token by token. Many tasks such as preference optimization, require the model to produce task-level output consisting of multiple tokens directly by…

Computation and Language · Computer Science 2025-01-30 Mingyu Derek Ma , Yanna Ding , Zijie Huang , Jianxi Gao , Yizhou Sun , Wei Wang

With the recent proliferation of Large Language Models (LLMs), there has been an increasing demand for tools to detect machine-generated text. The effective detection of machine-generated text face two pertinent problems: First, they are…

Computation and Language · Computer Science 2024-04-04 Mazal Bethany , Brandon Wherry , Emet Bethany , Nishant Vishwamitra , Anthony Rios , Peyman Najafirad

Modern language models operate on subword-tokenized text in order to make a trade-off between model size, inference speed, and vocabulary coverage. A side effect of this is that, during inference, models are evaluated by measuring the…

Computation and Language · Computer Science 2025-10-24 David Pohl , Marco Cognetta , Junyoung Lee , Naoaki Okazaki

Large Language Models (LLMs) are widely deployed in real-world applications, yet little is known about their training dynamics at the token level. Evaluation typically relies on aggregated training loss, measured at the batch level, which…

Computation and Language · Computer Science 2024-10-17 Andrea Pinto , Tomer Galanti , Randall Balestriero

The power of natural language generation models has provoked a flurry of interest in automatic methods to detect if a piece of text is human or machine-authored. The problem so far has been framed in a standard supervised way and consists…

Computation and Language · Computer Science 2021-11-05 Matthias Gallé , Jos Rozen , Germán Kruszewski , Hady Elsahar

Neural language models are increasingly deployed into APIs and websites that allow a user to pass in a prompt and receive generated text. Many of these systems do not reveal generation parameters. In this paper, we present methods to…

Machine Learning · Computer Science 2023-09-12 Daphne Ippolito , Nicholas Carlini , Katherine Lee , Milad Nasr , Yun William Yu

For open-ended language generation tasks such as storytelling and dialogue, choosing the right decoding algorithm is critical to controlling the tradeoff between generation quality and diversity. However, there presently exists no consensus…

Computation and Language · Computer Science 2020-04-23 Hugh Zhang , Daniel Duckworth , Daphne Ippolito , Arvind Neelakantan

Recent progress in pre-trained language models led to systems that are able to generate text of an increasingly high quality. While several works have investigated the fluency and grammatical correctness of such models, it is still unclear…

Despite the widespread use of Transformer-based text embedding models in NLP tasks, surprising 'sticky tokens' can undermine the reliability of embeddings. These tokens, when repeatedly inserted into sentences, pull sentence similarity…

Computation and Language · Computer Science 2025-07-25 Kexin Chen , Dongxia Wang , Yi Liu , Haonan Zhang , Wenhai Wang

An ideal detection system for machine generated content is supposed to work well on any generator as many more advanced LLMs come into existence day by day. Existing systems often struggle with accurately identifying AI-generated content…

Modern tokenizers employ deterministic algorithms to map text into a single "canonical" token sequence, yet the same string can be encoded as many non-canonical tokenizations using the tokenizer vocabulary. In this work, we investigate the…

Computation and Language · Computer Science 2026-02-04 Brian Siyuan Zheng , Alisa Liu , Orevaoghene Ahia , Jonathan Hayase , Yejin Choi , Noah A. Smith

Decoding strategies play a pivotal role in text generation for modern language models, yet a puzzling gap divides theory and practice. Surprisingly, strategies that should intuitively be optimal, such as Maximum a Posteriori (MAP), often…

Machine Learning · Computer Science 2025-05-20 Sijin Chen , Omar Hagrass , Jason M. Klusowski

This paper introduces a novel approach for identifying the possible large language models (LLMs) involved in text generation. Instead of adding an additional classification layer to a base LM, we reframe the classification task as a…

Computation and Language · Computer Science 2024-02-08 Yutian Chen , Hao Kang , Vivian Zhai , Liangze Li , Rita Singh , Bhiksha Raj

State-of-the-art language generation models can degenerate when applied to open-ended generation problems such as text completion, story generation, or dialog modeling. This degeneration usually shows up in the form of incoherence, lack of…

Computation and Language · Computer Science 2023-02-15 Kushal Arora , Timothy J. O'Donnell , Doina Precup , Jason Weston , Jackie C. K. Cheung

Machine-generated texts (MGTs) produced by large language models (LLMs) are increasingly prevalent across various applications, while their potential misuse in fake news propagation and phishing has raised serious concerns, highlighting the…

Computation and Language · Computer Science 2026-05-25 Chenwang Wu , Yiu-ming Cheung , Bo Han , Defu Lian

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

Large-scale generative models enabled the development of AI-powered code completion tools to assist programmers in writing code. However, much like other AI-powered tools, AI-powered code completions are not always accurate, potentially…

Human-Computer Interaction · Computer Science 2024-11-12 Helena Vasconcelos , Gagan Bansal , Adam Fourney , Q. Vera Liao , Jennifer Wortman Vaughan

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…