English
Related papers

Related papers: Establishing a Scale for Kullback-Leibler Divergen…

200 papers

In multi-instance (MI) learning, each object (bag) consists of multiple feature vectors (instances), and is most commonly regarded as a set of points in a multidimensional space. A different viewpoint is that the instances are realisations…

Machine Learning · Statistics 2018-10-16 Kajsa Møllersen , Jon Yngve Hardeberg , Fred Godtliebsen

Kullback-Leiber divergence has been widely used in Knowledge Distillation (KD) to compress Large Language Models (LLMs). Contrary to prior assertions that reverse Kullback-Leibler (RKL) divergence is mode-seeking and thus preferable over…

Computation and Language · Computer Science 2024-12-10 Taiqiang Wu , Chaofan Tao , Jiahao Wang , Runming Yang , Zhe Zhao , Ngai Wong

We consider learning with possibilistic supervision for multi-class classification. For each training instance, the supervision is a normalized possibility distribution that expresses graded plausibility over the classes. From this…

Artificial Intelligence · Computer Science 2026-04-03 Ismaïl Baaj , Pierre Marquis

We give an overview of statistical models and likelihood, together with two of its variants: penalized and hierarchical likelihood. The Kullback-Leibler divergence is referred to repeatedly, for defining the misspecification risk of a…

Statistics Theory · Mathematics 2008-09-01 Daniel Commenges

Large Language Models (LLMs) are widely used to evaluate natural language generation tasks as automated metrics. However, the likelihood, a measure of LLM's plausibility for a sentence, can vary due to superficial differences in sentences,…

Computation and Language · Computer Science 2025-11-11 Masanari Oi , Masahiro Kaneko , Ryuto Koike , Mengsay Loem , Naoaki Okazaki

This paper provides a detailed investigation of using the Kullback-Leibler (KL) Divergence as a way to compare and analyse game-levels, and hence to use the measure as the objective function of an evolutionary algorithm to evolve new…

Neural and Evolutionary Computing · Computer Science 2019-05-14 Simon M. Lucas , Vanessa Volz

Despite a growing interest in diffusion-based language models, existing work has not shown that these models can attain nontrivial likelihoods on standard language modeling benchmarks. In this work, we take the first steps towards closing…

Computation and Language · Computer Science 2023-05-31 Ishaan Gulrajani , Tatsunori B. Hashimoto

We present theoretical properties of the log-concave maximum likelihood estimator of a density based on an independent and identically distributed sample in $\mathbb{R}^d$. Our study covers both the case where the true underlying density is…

Statistics Theory · Mathematics 2009-09-01 Madeleine Cule , Richard Samworth

We study the approximation of arbitrary distributions $P$ on $d$-dimensional space by distributions with log-concave density. Approximation means minimizing a Kullback--Leibler-type functional. We show that such an approximation exists if…

Statistics Theory · Mathematics 2011-10-17 Lutz Duembgen , Richard Samworth , Dominic Schuhmacher

Increasing the number of parameters in language models is a common strategy to enhance their performance. However, smaller language models remain valuable due to their lower operational costs. Despite their advantages, smaller models…

Computation and Language · Computer Science 2024-10-16 Richard Diehl Martinez , Pietro Lesci , Paula Buttery

Complex, high-dimensional data is ubiquitous across many scientific disciplines, including machine learning, biology, and the social sciences. One of the primary methods of visualizing these datasets is with two-dimensional scatter plots…

Machine Learning · Computer Science 2025-10-13 Kiran Smelser , Kaviru Gunaratne , Jacob Miller , Stephen Kobourov

Masked Language Models (MLMs) have been successful in many natural language processing tasks. However, real-world stereotype biases are likely to be reflected in MLMs due to their learning from large text corpora. Most of the evaluation…

Computation and Language · Computer Science 2023-09-04 Yang Liu , Yuexian Hou

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

Reverse Kullback-Leibler (RKL) divergence has recently emerged as the preferred objective for large language model (LLM) distillation, consistently outperforming forward KL (FKL), particularly in regimes with large vocabularies and…

Machine Learning · Computer Science 2026-04-02 Hoang-Chau Luong , Dat Ba Tran , Lingwei Chen

Recent works have proposed various explanations for the ability of modern large language models (LLMs) to perform in-context prediction. We propose an alternative conceptual viewpoint from an information-geometric and statistical…

Information Theory · Computer Science 2026-02-23 Sreejith Sreekumar , Nir Weinberger

Large language models (LLMs) are demonstrably capable of cross-lingual transfer, but can produce inconsistent output when prompted with the same queries written in different languages. To understand how language models are able to…

Computation and Language · Computer Science 2025-09-29 Zheng Wei Lim , Alham Fikri Aji , Trevor Cohn

We consider the problem of estimating probability density functions based on sample data, using a finite mixture of densities from some component class. To this end, we introduce the $h$-lifted Kullback--Leibler (KL) divergence as a…

Machine Learning · Statistics 2024-12-24 Mark Chiu Chong , Hien Duy Nguyen , TrungTin Nguyen

Estimating the Kullback-Leibler (KL) divergence between random variables is a fundamental problem in statistical analysis. For continuous random variables, traditional information-theoretic estimators scale poorly with dimension and/or…

Machine Learning · Computer Science 2025-10-08 Mikil Foss , Andrew Lamperski

Many applications of large language models (LLMs) require long-context understanding, but models continue to struggle with such tasks. We hypothesize that conventional next-token prediction training could contribute to this, because each…

Computation and Language · Computer Science 2025-03-13 Falko Helm , Nico Daheim , Iryna Gurevych

Article discusses the application of Kullback-Leibler divergence to the recognition of speech signals and suggests three algorithms implementing this divergence criterion: correlation algorithm, spectral algorithm and filter algorithm.…

Artificial Intelligence · Computer Science 2007-05-23 Igor Bocharov , Pavel Lukin