Papers › ShareGPT4V: Improving Large Multi-Modal Models with Better Captions

ShareGPT4V: Improving Large Multi-Modal Models with Better Captions

21 Nov 2023arXiv:2311.12793archive 2025-07-28

Lin Chen, Jinsong Li, Xiaoyi Dong, Pan Zhang, Conghui He, Jiaqi Wang, Feng Zhao, Dahua Lin

In the realm of large multi-modal models (LMMs), efficient modality alignment is crucial yet often constrained by the scarcity of high-quality image-text data. To address this bottleneck, we introduce the ShareGPT4V dataset, a pioneering large-scale resource featuring 1.2 million highly descriptive captions, which surpasses existing datasets in diversity and information content, covering world knowledge, object properties, spatial relationships, and aesthetic evaluations. Specifically, ShareGPT4V originates from a curated 100K high-quality captions collected from advanced GPT4-Vision and has been expanded to 1.2M with a superb caption model trained on this subset. ShareGPT4V first demonstrates its effectiveness for the Supervised Fine-Tuning (SFT) phase, by substituting an equivalent quantity of detailed captions in existing SFT datasets with a subset of our high-quality captions, significantly enhancing the LMMs like LLaVA-7B, LLaVA-1.5-13B, and Qwen-VL-Chat-7B on the MME and MMBench benchmarks, with respective gains of 222.8/22.0/22.3 and 2.7/1.3/1.5. We further incorporate ShareGPT4V data into both the pre-training and SFT phases, obtaining ShareGPT4V-7B, a superior LMM based on a simple architecture that has remarkable performance across a majority of the multi-modal benchmarks. This project is available at https://ShareGPT4V.github.io to serve as a pivotal resource for advancing the LMMs community.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

DescriptiveMMEVisual Question AnsweringWorld Knowledgevisual instruction following

Datasets

Introduced by this paper, per the archive.

ShareGPT4V

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Visual Question Answering MM-Vet ShareGPT4V-13B GPT-4 score 43.1 #96 of 231 Archive leaderboard report
Visual Question Answering MM-Vet ShareGPT4V-13B Params 13B #96 of 231 Archive leaderboard report
Visual Question Answering MM-Vet ShareGPT4V-7B GPT-4 score 37.6 #130 of 231 Archive leaderboard report
Visual Question Answering MM-Vet ShareGPT4V-7B Params 7B #130 of 231 Archive leaderboard report
visual instruction following LLaVA-Bench ShareGPT4V-13B avg score 79.9 #2 of 8 Archive leaderboard report
visual instruction following LLaVA-Bench ShareGPT4V-7B avg score 72.6 #3 of 8 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

SFT

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections