English
Related papers

Related papers: On the probability-quality paradox in language gen…

200 papers

In safety-critical applications, language models should be able to characterize their uncertainty with meaningful probabilities. Many uncertainty quantification approaches require supervised data; however, finding suitable unseen…

Computation and Language · Computer Science 2026-05-14 Sophia Hager , Simon Zeng , Nicholas Andrews

We study the problem of entropy calibration, which asks whether a language model's entropy over generations matches its log loss on human text. Past work found that models are miscalibrated, with entropy per step increasing as generations…

Computation and Language · Computer Science 2026-01-14 Steven Cao , Gregory Valiant , Percy Liang

Large language models (LLMs) have demonstrated impressive capabilities in natural language generation. However, their output quality can be inconsistent, posing challenges for generating natural language from logical forms (LFs). This task…

Computation and Language · Computer Science 2023-09-22 Levon Haroutunian , Zhuang Li , Lucian Galescu , Philip Cohen , Raj Tumuluri , Gholamreza Haffari

Language models (LMs) are trained on billions of tokens in an attempt to recover the true language distribution. Still, vanilla random sampling from LMs yields low quality generations. Decoding algorithms attempt to restrict the LM…

Machine Learning · Computer Science 2026-01-06 Kareem Ahmed , Sameer Singh

Natural language generation (NLG) is a critical component in spoken dialogue systems. Classic NLG can be divided into two phases: (1) sentence planning: deciding on the overall sentence structure, (2) surface realization: determining…

Computation and Language · Computer Science 2018-08-10 Shang-Yu Su , Kai-Ling Lo , Yi-Ting Yeh , Yun-Nung Chen

Large language models (LM) generate remarkably fluent text and can be efficiently adapted across NLP tasks. Measuring and guaranteeing the quality of generated text in terms of safety is imperative for deploying LMs in the real world; to…

Long Short-Term Memory (LSTM) networks have recently shown remarkable performance in several tasks dealing with natural language generation, such as image captioning or poetry composition. Yet, only few works have analyzed text generated by…

Computation and Language · Computer Science 2019-04-16 Marco Lippi , Marcelo A Montemurro , Mirko Degli Esposti , Giampaolo Cristadoro

Language models increasingly rely on massive web dumps for diverse text data. However, these sources are rife with undesirable content. As such, resources like Wikipedia, books, and newswire often serve as anchors for automatically…

Computation and Language · Computer Science 2022-01-27 Suchin Gururangan , Dallas Card , Sarah K. Dreier , Emily K. Gade , Leroy Z. Wang , Zeyu Wang , Luke Zettlemoyer , Noah A. Smith

Language modeling, a central task in natural language processing, involves estimating a probability distribution over strings. In most cases, the estimated distribution sums to 1 over all finite strings. However, in some pathological cases,…

Computation and Language · Computer Science 2023-08-23 Li Du , Lucas Torroba Hennigen , Tiago Pimentel , Clara Meister , Jason Eisner , Ryan Cotterell

Concept-to-text generation typically employs a pipeline architecture, which often leads to suboptimal texts. Content selection, for example, may greedily select the most important facts, which may require, however, too many words to…

Computation and Language · Computer Science 2018-11-02 Gerasimos Lampouras , Ion Androutsopoulos

Contemporary theories model language processing as integrating both top-down expectations and bottom-up inputs. One major prediction of such models is that the quality of the bottom-up inputs modulates ease of processing -- noisy inputs…

Computation and Language · Computer Science 2025-10-28 Cui Ding , Yanning Yin , Lena A. Jäger , Ethan Gotlieb Wilcox

Recent works on language identification and generation have established tight statistical rates at which these tasks can be achieved. These works typically operate under a strong realizability assumption: that the input data is drawn from…

Machine Learning · Computer Science 2026-04-23 Mikael Møller Høgsgaard , Chirag Pabbaraju

Applications of large language models often involve the generation of free-form responses, in which case uncertainty quantification becomes challenging. This is due to the need to identify task-specific uncertainties (e.g., about the…

Computation and Language · Computer Science 2024-10-21 Ziyu Wang , Chris Holmes

While conditional language models have greatly improved in their ability to output high-quality natural language, many NLP applications benefit from being able to generate a diverse set of candidate sequences. Diverse decoding strategies…

Computation and Language · Computer Science 2019-06-18 Daphne Ippolito , Reno Kriz , Maria Kustikova , João Sedoc , Chris Callison-Burch

Shannon entropy is often a quantity of interest to linguists studying the communicative capacity of human language. However, entropy must typically be estimated from observed data because researchers do not have access to the underlying…

Computation and Language · Computer Science 2022-04-06 Aryaman Arora , Clara Meister , Ryan Cotterell

Many challenges in natural language processing require generating text, including language translation, dialogue generation, and speech recognition. For all of these problems, text generation becomes more difficult as the text becomes…

Computation and Language · Computer Science 2018-10-23 Mehdi Drissi , Olivia Watkins , Jugal Kalita

Most of the existing text generative steganographic methods are based on coding the conditional probability distribution of each word during the generation process, and then selecting specific words according to the secret information, so…

Computation and Language · Computer Science 2020-06-16 Zhongliang Yang , Baitao Gong , Yamin Li , Jinshuai Yang , Zhiwen Hu , Yongfeng Huang

There is much debate over the degree to which language learning is governed by innate language-specific biases, or acquired through cognition-general principles. Here we examine the probabilistic language acquisition hypothesis on three…

Computation and Language · Computer Science 2010-06-17 Anne S. Hsu , Nick Chater , Paul M. B. Vitanyi

The large size and complex decision mechanisms of state-of-the-art text classifiers make it difficult for humans to understand their predictions, leading to a potential lack of trust by the users. These issues have led to the adoption of…

What makes some types of languages more probable than others? For instance, we know that almost all spoken languages contain the vowel phoneme /i/; why should that be? The field of linguistic typology seeks to answer these questions and,…

Computation and Language · Computer Science 2018-07-10 Ryan Cotterell , Jason Eisner