{"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/llm4vis-explainable-visualization","title":"LLM4Vis: Explainable Visualization Recommendation using ChatGPT","arxiv_id":"2310.07652","date":"2023-10-11","proceeding":null,"authors":["Lei Wang","Songheng Zhang","Yun Wang","Ee-Peng Lim","Yong Wang"],"abstract":"Data visualization is a powerful tool for exploring and communicating insights in various domains. To automate visualization choice for datasets, a task known as visualization recommendation has been proposed. Various machine-learning-based approaches have been developed for this purpose, but they often require a large corpus of dataset-visualization pairs for training and lack natural explanations for their results. To address this research gap, we propose LLM4Vis, a novel ChatGPT-based prompting approach to perform visualization recommendation and return human-like explanations using very few demonstration examples. Our approach involves feature description, demonstration example selection, explanation generation, demonstration example construction, and inference steps. To obtain demonstration examples with high-quality explanations, we propose a new explanation generation bootstrapping to iteratively refine generated explanations by considering the previous generation and template-based hint. Evaluations on the VizML dataset show that LLM4Vis outperforms or performs similarly to supervised learning models like Random Forest, Decision Tree, and MLP in both few-shot and zero-shot settings. The qualitative evaluation also shows the effectiveness of explanations generated by LLM4Vis. We make our code publicly available at \\href{https://github.com/demoleiwang/LLM4Vis}{https://github.com/demoleiwang/LLM4Vis}.","url_abs":"https://arxiv.org/abs/2310.07652v2","url_pdf":"https://arxiv.org/pdf/2310.07652v2.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":"llm4vis-explainable-visualization","repo_url":"https://github.com/demoleiwang/llm4vis","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"data-visualization","task_name":"Data Visualization"},{"task_slug":"explanation-generation","task_name":"Explanation Generation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2310.07652","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.07652"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"deterministic:regex_extraction","url":"https://github.com/demoleiwang/LLM4Vis","reach":{"status":"ok"}}],"summary":{"ran":3,"unverified":1},"by_repo_kind":{"official":{"samples":4,"ran":3,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":4,"samples":[{"code_sha256_prefix":"355fdce9c6bdafec","entry":"dispatch_openai_api_requests","repo":"demoleiwang/LLM4Vis","repo_kind":"official","path":"utils.py","file_url":"https://github.com/demoleiwang/LLM4Vis/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"355fdce9c6bdafec"}},{"code_sha256_prefix":"b22773c4b6284043","entry":"dispatch_openai_requests","repo":"demoleiwang/LLM4Vis","repo_kind":"official","path":"utils.py","file_url":"https://github.com/demoleiwang/LLM4Vis/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b22773c4b6284043"}},{"code_sha256_prefix":"005bceded2b9a9c6","entry":"read_json","repo":"demoleiwang/LLM4Vis","repo_kind":"official","path":"utils.py","file_url":"https://github.com/demoleiwang/LLM4Vis/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"005bceded2b9a9c6"}},{"code_sha256_prefix":"9dd19b0de55e6061","entry":"data_prepare_split","repo":"demoleiwang/LLM4Vis","repo_kind":"official","path":"data_prepare.py","file_url":"https://github.com/demoleiwang/LLM4Vis/blob/HEAD/data_prepare.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"9dd19b0de55e6061"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}