Guardado en:
Detalles Bibliográficos
Autores principales: Fu, Tairan, González, Miguel, Conde, Javier, Merino-Gómez, Elena, Reviriego, Pedro
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:https://arxiv.org/abs/2505.10862
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866916739513581568
author Fu, Tairan
González, Miguel
Conde, Javier
Merino-Gómez, Elena
Reviriego, Pedro
author_facet Fu, Tairan
González, Miguel
Conde, Javier
Merino-Gómez, Elena
Reviriego, Pedro
contents Multimodal Large Language Models which can answer complex questions on an image struggle to tell the time on analog clocks. This is probably due to the lack of images with clocks at different times in their training set. In this work we explore this issue with one of the latest MLLMs: GPT-4.1 to understand why MLLMs fail to tell the time and whether fine-tuning can solve the problem. The results show how models are making progress in reading the time on analog clocks. But have they really learned to do it, or have they only learned patterns in their training datasets? In this work we put the models to the test with different clocks to illustrate the limitations of MLLMs to abstract and generalize.
format Preprint
id arxiv_https___arxiv_org_abs_2505_10862
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Have Multimodal Large Language Models (MLLMs) Really Learned to Tell the Time on Analog Clocks?
Fu, Tairan
González, Miguel
Conde, Javier
Merino-Gómez, Elena
Reviriego, Pedro
Computation and Language
I.2.7
Multimodal Large Language Models which can answer complex questions on an image struggle to tell the time on analog clocks. This is probably due to the lack of images with clocks at different times in their training set. In this work we explore this issue with one of the latest MLLMs: GPT-4.1 to understand why MLLMs fail to tell the time and whether fine-tuning can solve the problem. The results show how models are making progress in reading the time on analog clocks. But have they really learned to do it, or have they only learned patterns in their training datasets? In this work we put the models to the test with different clocks to illustrate the limitations of MLLMs to abstract and generalize.
title Have Multimodal Large Language Models (MLLMs) Really Learned to Tell the Time on Analog Clocks?
topic Computation and Language
I.2.7
url https://arxiv.org/abs/2505.10862