{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/sharegpt4v-improving-large-multi-modal-models","title":"ShareGPT4V: Improving Large Multi-Modal Models with Better Captions","arxiv_id":"2311.12793","date":"2023-11-21","proceeding":null,"authors":["Lin Chen","Jinsong Li","Xiaoyi Dong","Pan Zhang","Conghui He","Jiaqi Wang","Feng Zhao","Dahua Lin"],"abstract":"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.","url_abs":"https://arxiv.org/abs/2311.12793v2","url_pdf":"https://arxiv.org/pdf/2311.12793v2.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":"sharegpt4v-improving-large-multi-modal-models","repo_url":"https://github.com/InternLM/InternLM-XComposer/tree/main/projects/ShareGPT4V","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"descriptive","task_name":"Descriptive"},{"task_slug":"mme","task_name":"MME"},{"task_slug":"visual-question-answering-1","task_name":"Visual Question Answering"},{"task_slug":"world-knowledge","task_name":"World Knowledge"},{"task_slug":"visual-instruction-following","task_name":"visual instruction following"}],"methods":[{"method_slug":"sft","method_name":"SFT"}],"datasets_introduced":[{"slug":"sharegpt4v","name":"ShareGPT4V","full_name":""}],"methods_introduced":[],"results":[{"leaderboard":"/sota/visual-question-answering-on-mm-vet","task":"Visual Question Answering","dataset":"MM-Vet","model":"ShareGPT4V-13B","rank_in_archive_order":96,"of":231,"metrics":{"GPT-4 score":"43.1","Params":"13B"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-on-mm-vet","task":"Visual Question Answering","dataset":"MM-Vet","model":"ShareGPT4V-7B","rank_in_archive_order":130,"of":231,"metrics":{"GPT-4 score":"37.6","Params":"7B"},"uses_additional_data":false},{"leaderboard":"/sota/visual-instruction-following-on-llava-bench","task":"visual instruction following","dataset":"LLaVA-Bench","model":"ShareGPT4V-13B","rank_in_archive_order":2,"of":8,"metrics":{"avg score":"79.9"},"uses_additional_data":false},{"leaderboard":"/sota/visual-instruction-following-on-llava-bench","task":"visual instruction following","dataset":"LLaVA-Bench","model":"ShareGPT4V-7B","rank_in_archive_order":3,"of":8,"metrics":{"avg score":"72.6"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2311.12793","atlas_url":"https://app.syntology.ai/?focus=2311.12793","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2311.12793"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2311.12793\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2311.12793"},"call":"get_concepts_for_paper(arxiv_id=\"2311.12793\")"}],"by_repo":[{"repo":"InternLM/InternLM-XComposer","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2402.14767"],"harvested_for_calls":[{"arxiv_id":"2402.14767","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2402.14767"},"call":"get_harvested_code_for_paper(arxiv_id=\"2402.14767\")"}]}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"e8a616a3cae592aae4e77392281195161b4c02334845e7a576de1990c1750a85","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}