paper-with-me

홈 › Papers

Local Normalization Distortion and the Thermodynamic Formalism of Decoding Strategies for Large Language Models

2025-03-27 · Tom Kempton, Stuart Burrell

Advances in hardware and language model architecture have spurred a revolution in natural language generation. However, autoregressive models compute probability distributions over next-token choices, and sampling from these distributions, known as decoding, has received significantly less attention than other design choices. Existing decoding strategies are largely based on heuristics, resulting in methods that are hard to apply or improve in a principled manner. We develop the theory of decoding strategies for language models by expressing popular decoding algorithms as equilibrium states in the language of ergodic theory and stating the functions they optimize. Using this, we analyze the effect of the local normalization step of top-k, nucleus, and temperature sampling, used to make probabilities sum to one. We argue that local normalization distortion is a fundamental defect of decoding strategies and quantify the size of this distortion and its effect on mathematical proxies for the quality and diversity of generated text. Contrary to the prevailing explanation, we argue that the major cause of the under-performance of top-k sampling relative to nucleus sampling is local normalization distortion. This yields conclusions for the future design of decoding algorithms and the detection of machine-generated text.

📄 PDF Abstract BibTeX arXiv:2503.21929

Code (0)

등록된 구현이 없습니다.

Tasks

Text Generation

Methods 이 논문이 사용한 방법론

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Attention 설명 없음

Similar Papers 제목 키워드 기반

Sentence Compression as Tree Transduction

2014-01-15 · Trevor Anthony Cohn, Mirella Lapata

This paper presents a tree-to-tree transduction method for sentence compression. Our model is based on synchronous tree substitution grammar, a formalism that allows local distortion of the tree topology and can thus nat…

Local DistortionSentenceSentence Compression

Thermodynamic Formalism in Neuronal Dynamics and Spike Train Statistics

2020-11-18 · Rodrigo Cofré, Cesar Maldonado, Bruno Cessac

The Thermodynamic Formalism provides a rigorous mathematical framework to study quantitative and qualitative aspects of dynamical systems. At its core there is a variational principle corresponding, in its simplest form,…

A comparison of Single- and Double-generator formalisms for Thermodynamics-Informed Neural Networks

2024-04-01 · Pau Urdeitx, Icíar Alfaro, David González, Francisco Chinesta 외

The development of inductive biases has been shown to be a very effective way to increase the accuracy and robustness of neural networks, particularly when they are used to predict physical phenomena. These biases signif…

valid

Port-metriplectic neural networks: thermodynamics-informed machine learning of complex physical systems

2022-11-03 · Quercus Hernández, Alberto Badías, Francisco Chinesta, Elías Cueto

We develop inductive biases for the machine learning of complex physical systems based on the port-Hamiltonian formalism. To satisfy by construction the principles of thermodynamics in the learned physics (conservation o…

Local and Global Decoding in Text Generation

2024-10-14 · Daniel Gareev, Thomas Hofmann, Ezhilmathi Krishnasamy, Tiago Pimentel

Text generation, a key component in applications such as dialogue systems, relies on decoding algorithms that sample strings from a language model distribution. Traditional methods, such as top-$k$ and top-$\pi$, apply l…

Language ModelingLanguage ModellingText Generation