{"ID":2858651,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.06782","arxiv_id":"2510.06782","title":"GPT-5 Model Corrected GPT-4V's Chart Reading Errors, Not Prompting","abstract":"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.","short_abstract":"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-...","url_abs":"https://arxiv.org/abs/2510.06782","url_pdf":"https://arxiv.org/pdf/2510.06782v1","authors":"[\"Kaichun Yang\",\"Jian Chen\"]","published":"2025-10-08T09:09:29Z","proceeding":"cs.HC","tasks":"[\"cs.HC\",\"cs.CL\",\"cs.CV\"]","methods":"[\"Large Language Model\",\"Language Model\"]","project_urls":"[\"https://osf.io/u78td/?view_only=6b075584311f48e991c39335c840ded3\",\"https://drive.google.com/file/d/1ll8WWZDf7cCNcfNWrLViWt8GwDNSvVrp/view\"]","has_code":false}