{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/to-see-is-to-believe-prompting-gpt-4v-for","title":"To See is to Believe: Prompting GPT-4V for Better Visual Instruction Tuning","arxiv_id":"2311.07574","date":"2023-11-13","proceeding":null,"authors":["Junke Wang","Lingchen Meng","Zejia Weng","Bo He","Zuxuan Wu","Yu-Gang Jiang"],"abstract":"Existing visual instruction tuning methods typically prompt large language models with textual descriptions to generate instruction-following data. Despite the promising performance achieved, these descriptions are derived from image annotations, which are oftentimes coarse-grained. Furthermore, the instructions might even contradict the visual content without observing the entire visual context. To address this challenge, we introduce a fine-grained visual instruction dataset, LVIS-Instruct4V, which contains 220K visually aligned and context-aware instructions produced by prompting the powerful GPT-4V with images from LVIS. Through experimental validation and case studies, we demonstrate that high-quality visual instructional data could improve the performance of LLaVA-1.5, a state-of-the-art large multimodal model, across a wide spectrum of benchmarks by clear margins. Notably, by simply replacing the LLaVA-Instruct with our LVIS-Instruct4V, we achieve better results than LLaVA on most challenging LMM benchmarks, e.g., LLaVA$^w$ (76.7 vs. 70.7) and MM-Vet (40.2 vs. 35.4). We release our data and model at https://github.com/X2FD/LVIS-INSTRUCT4V.","url_abs":"https://arxiv.org/abs/2311.07574v2","url_pdf":"https://arxiv.org/pdf/2311.07574v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"to-see-is-to-believe-prompting-gpt-4v-for","repo_url":"https://github.com/x2fd/lvis-instruct4v","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"to-see-is-to-believe-prompting-gpt-4v-for","repo_url":"https://github.com/h-zhao1997/cobra","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"instruction-following","task_name":"Instruction Following"},{"task_slug":null,"task_name":"MM-Vet"},{"task_slug":"visual-question-answering-1","task_name":"Visual Question Answering"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/visual-question-answering-on-mm-vet","task":"Visual Question Answering","dataset":"MM-Vet","model":"LLaVA-1.5 (LVIS-Instrcut4V)","rank_in_archive_order":110,"of":231,"metrics":{"GPT-4 score":"40.2","Params":"13B"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2311.07574","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}