{"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/vis-shepherd-constructing-critic-for-llm","title":"VIS-Shepherd: Constructing Critic for LLM-based Data Visualization Generation","arxiv_id":"2506.13326","date":"2025-06-16","proceeding":null,"authors":["Bo Pan","Yixiao Fu","Ke Wang","Junyu Lu","Lunke Pan","Ziyang Qian","Yuhan Chen","Guoliang Wang","Yitao Zhou","Li Zheng","Yinghao Tang","Zhen Wen","Yuchen Wu","Junhua Lu","Biao Zhu","Minfeng Zhu","Bo Zhang","Wei Chen"],"abstract":"Data visualization generation using Large Language Models (LLMs) has shown promising results but often produces suboptimal visualizations that require human intervention for improvement. In this work, we introduce VIS-Shepherd, a specialized Multimodal Large Language Model (MLLM)-based critic to evaluate and provide feedback for LLM-generated data visualizations. At the core of our approach is a framework to construct a high-quality visualization critique dataset, where we collect human-created visualization instances, synthesize corresponding LLM-generated instances, and construct high-quality critiques. We conduct both model-based automatic evaluation and human preference studies to evaluate the effectiveness of our approach. Our experiments show that even small (7B parameters) open-source MLLM models achieve substantial performance gains by leveraging our high-quality visualization critique dataset, reaching levels comparable to much larger open-source or even proprietary models. Our work demonstrates significant potential for MLLM-based automated visualization critique and indicates promising directions for enhancing LLM-based data visualization generation. Our project page: https://github.com/bopan3/VIS-Shepherd.","url_abs":"https://arxiv.org/abs/2506.13326v1","url_pdf":"https://arxiv.org/pdf/2506.13326v1.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":"vis-shepherd-constructing-critic-for-llm","repo_url":"https://github.com/bopan3/vis-shepherd","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"data-visualization","task_name":"Data Visualization"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"large-language-model","task_name":"Large Language Model"},{"task_slug":"multimodal-large-language-model","task_name":"Multimodal Large Language Model"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2506.13326","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.13326"}},"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":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/bopan3/vis-shepherd","reach":{"status":"ok"}}],"summary":{"unverified":6},"by_repo_kind":{"official":{"samples":6,"ran":0,"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":6,"samples":[{"code_sha256_prefix":"a9b7011df230e892","entry":"clean_json_string","repo":"bopan3/vis-shepherd","repo_kind":"official","path":"Evaluation/processors/coarseFilterProcessor.py","file_url":"https://github.com/bopan3/vis-shepherd/blob/HEAD/Evaluation/processors/coarseFilterProcessor.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":"a9b7011df230e892"}},{"code_sha256_prefix":"c8bfc693108e05b3","entry":"process_single_file","repo":"bopan3/vis-shepherd","repo_kind":"official","path":"Evaluation/run_parallel_autoEvaluateLikert.py","file_url":"https://github.com/bopan3/vis-shepherd/blob/HEAD/Evaluation/run_parallel_autoEvaluateLikert.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":"c8bfc693108e05b3"}},{"code_sha256_prefix":"cb9cf6b41f0ea2de","entry":"read_image_as_base64","repo":"bopan3/vis-shepherd","repo_kind":"official","path":"Evaluation/run_single_autoEvaluateLikert.py","file_url":"https://github.com/bopan3/vis-shepherd/blob/HEAD/Evaluation/run_single_autoEvaluateLikert.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":"cb9cf6b41f0ea2de"}},{"code_sha256_prefix":"72b2964a4e373380","entry":"read_json_file","repo":"bopan3/vis-shepherd","repo_kind":"official","path":"Evaluation/run_single_autoEvaluateLikert.py","file_url":"https://github.com/bopan3/vis-shepherd/blob/HEAD/Evaluation/run_single_autoEvaluateLikert.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":"72b2964a4e373380"}},{"code_sha256_prefix":"e9dedc0a23670508","entry":"read_text_file","repo":"bopan3/vis-shepherd","repo_kind":"official","path":"Evaluation/run_single_autoEvaluateLikert.py","file_url":"https://github.com/bopan3/vis-shepherd/blob/HEAD/Evaluation/run_single_autoEvaluateLikert.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":"e9dedc0a23670508"}},{"code_sha256_prefix":"70f351e15314696d","entry":"resize_image_if_needed","repo":"bopan3/vis-shepherd","repo_kind":"official","path":"Evaluation/llmAPI/llmAPI.py","file_url":"https://github.com/bopan3/vis-shepherd/blob/HEAD/Evaluation/llmAPI/llmAPI.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":"70f351e15314696d"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}