Salvato in:
Dettagli Bibliografici
Autori principali: Yang, Kaichun, Chen, Jian
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2510.06782
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866909831072317440
author Yang, Kaichun
Chen, Jian
author_facet Yang, Kaichun
Chen, Jian
contents We present a quantitative evaluation to understand the effect of zero-shot large-language model (LLMs) and prompting uses on chart reading tasks. We asked LLMs to answer 107 visualization questions to compare inference accuracies between the agentic GPT-5 and multimodal GPT-4V, for difficult image instances, where GPT-4V failed to produce correct answers. Our results show that model architecture dominates the inference accuracy: GPT5 largely improved accuracy, while prompt variants yielded only small effects. Pre-registration of this work is available here: https://osf.io/u78td/?view_only=6b075584311f48e991c39335c840ded3; the Google Drive materials are here:https://drive.google.com/file/d/1ll8WWZDf7cCNcfNWrLViWt8GwDNSvVrp/view.
format Preprint
id arxiv_https___arxiv_org_abs_2510_06782
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle GPT-5 Model Corrected GPT-4V's Chart Reading Errors, Not Prompting
Yang, Kaichun
Chen, Jian
Human-Computer Interaction
Computation and Language
Computer Vision and Pattern Recognition
We present a quantitative evaluation to understand the effect of zero-shot large-language model (LLMs) and prompting uses on chart reading tasks. We asked LLMs to answer 107 visualization questions to compare inference accuracies between the agentic GPT-5 and multimodal GPT-4V, for difficult image instances, where GPT-4V failed to produce correct answers. Our results show that model architecture dominates the inference accuracy: GPT5 largely improved accuracy, while prompt variants yielded only small effects. Pre-registration of this work is available here: https://osf.io/u78td/?view_only=6b075584311f48e991c39335c840ded3; the Google Drive materials are here:https://drive.google.com/file/d/1ll8WWZDf7cCNcfNWrLViWt8GwDNSvVrp/view.
title GPT-5 Model Corrected GPT-4V's Chart Reading Errors, Not Prompting
topic Human-Computer Interaction
Computation and Language
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2510.06782