Is Information Density Uniform when Utterances are Grounded on Perception and Discourse?

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Gay, Matteo, Haley, Coleman, Giulianelli, Mario, Ponti, Edoardo
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866908836116299776
author Gay, Matteo
Haley, Coleman
Giulianelli, Mario
Ponti, Edoardo
author_facet Gay, Matteo
Haley, Coleman
Giulianelli, Mario
Ponti, Edoardo
contents The Uniform Information Density (UID) hypothesis posits that speakers are subject to a communicative pressure to distribute information evenly within utterances, minimising surprisal variance. While this hypothesis has been tested empirically, prior studies are limited exclusively to text-only inputs, abstracting away from the perceptual context in which utterances are produced. In this work, we present the first computational study of UID in visually grounded settings. We estimate surprisal using multilingual vision-and-language models over image-caption data in 30 languages and visual storytelling data in 13 languages, together spanning 11 families. We find that grounding on perception consistently smooths the distribution of information, increasing both global and local uniformity across typologically diverse languages compared to text-only settings. In visual narratives, grounding in both image and discourse contexts has additional effects, with the strongest surprisal reductions occurring at the onset of discourse units. Overall, this study takes a first step towards modelling the temporal dynamics of information flow in ecologically plausible, multimodal language use, and finds that grounded language exhibits greater information uniformity, supporting a context-sensitive formulation of UID.
format Preprint
id arxiv_https___arxiv_org_abs_2602_14653
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Is Information Density Uniform when Utterances are Grounded on Perception and Discourse?
Gay, Matteo
Haley, Coleman
Giulianelli, Mario
Ponti, Edoardo
Computation and Language
The Uniform Information Density (UID) hypothesis posits that speakers are subject to a communicative pressure to distribute information evenly within utterances, minimising surprisal variance. While this hypothesis has been tested empirically, prior studies are limited exclusively to text-only inputs, abstracting away from the perceptual context in which utterances are produced. In this work, we present the first computational study of UID in visually grounded settings. We estimate surprisal using multilingual vision-and-language models over image-caption data in 30 languages and visual storytelling data in 13 languages, together spanning 11 families. We find that grounding on perception consistently smooths the distribution of information, increasing both global and local uniformity across typologically diverse languages compared to text-only settings. In visual narratives, grounding in both image and discourse contexts has additional effects, with the strongest surprisal reductions occurring at the onset of discourse units. Overall, this study takes a first step towards modelling the temporal dynamics of information flow in ecologically plausible, multimodal language use, and finds that grounded language exhibits greater information uniformity, supporting a context-sensitive formulation of UID.
title Is Information Density Uniform when Utterances are Grounded on Perception and Discourse?
topic Computation and Language
url https://arxiv.org/abs/2602.14653