{"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/mmc-advancing-multimodal-chart-understanding","title":"MMC: Advancing Multimodal Chart Understanding with Large-scale Instruction Tuning","arxiv_id":"2311.10774","date":"2023-11-15","proceeding":null,"authors":["Fuxiao Liu","Xiaoyang Wang","Wenlin Yao","Jianshu Chen","Kaiqiang Song","Sangwoo Cho","Yaser Yacoob","Dong Yu"],"abstract":"With the rapid development of large language models (LLMs) and their integration into large multimodal models (LMMs), there has been impressive progress in zero-shot completion of user-oriented vision-language tasks. However, a gap remains in the domain of chart image understanding due to the distinct abstract components in charts. To address this, we introduce a large-scale MultiModal Chart Instruction (\\textbf{MMC-Instruction}) dataset comprising 600k instances supporting diverse tasks and chart types. Leveraging this data, we develop MultiModal Chart Assistant (\\textbf{MMCA}), an LMM that achieves state-of-the-art performance on existing chart QA benchmarks. Recognizing the need for a comprehensive evaluation of LMM chart understanding, we also propose a MultiModal Chart Benchmark (\\textbf{MMC-Benchmark}), a comprehensive human-annotated benchmark with nine distinct tasks evaluating reasoning capabilities over charts. Extensive experiments on MMC-Benchmark reveal the limitations of existing LMMs on correctly interpreting charts, even for the most recent GPT-4V model. Our work provides an instruction-tuning methodology and benchmark to advance multimodal understanding of charts. Code and data are available at https://github.com/FuxiaoLiu/MMC.","url_abs":"https://arxiv.org/abs/2311.10774v2","url_pdf":"https://arxiv.org/pdf/2311.10774v2.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":"mmc-advancing-multimodal-chart-understanding","repo_url":"https://github.com/fuxiaoliu/mmc","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"GPL-3.0"}},{"paper_slug":"mmc-advancing-multimodal-chart-understanding","repo_url":"https://github.com/FuxiaoLiu/LRV-Instruction","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"paper_slug":"mmc-advancing-multimodal-chart-understanding","repo_url":"https://github.com/FuxiaoLiu/VisualNews-Repository","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"mmc-advancing-multimodal-chart-understanding","repo_url":"https://github.com/tianyi-lab/hallusionbench","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"paper_slug":"mmc-advancing-multimodal-chart-understanding","repo_url":"https://github.com/yangyucheng000/Paper-4/tree/main/mm_MindSpore","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"mmc-advancing-multimodal-chart-understanding","repo_url":"https://github.com/yangyucheng000/papercode-2/tree/main/mm_MindSpore-main","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null}],"tasks":[{"task_slug":"chart-understanding","task_name":"Chart Understanding"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2311.10774","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.10774"}},"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/FuxiaoLiu/LRV-Instruction","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/yangyucheng000/papercode-2/tree/main/mm_MindSpore-main","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/FuxiaoLiu/VisualNews-Repository","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/tianyi-lab/hallusionbench","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/yangyucheng000/Paper-4/tree/main/mm_MindSpore","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/fuxiaoliu/mmc","reach":{"status":"ok","spdx":"GPL-3.0"}}],"summary":{"ran":6,"ran_fixture":1,"ran_violates":1,"ran_draft_wrong":1,"unverified":10},"by_repo_kind":{"official":{"samples":3,"ran":0,"repositories":1},"listed":{"samples":16,"ran":9,"repositories":3}},"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":9,"samples":[{"code_sha256_prefix":"c878d399a34f5c48","entry":"accuracy","repo":"FuxiaoLiu/VisualNews-Repository","repo_kind":"listed","path":"model/utils.py","file_url":"https://github.com/FuxiaoLiu/VisualNews-Repository/blob/HEAD/model/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":"c878d399a34f5c48"}},{"code_sha256_prefix":"9b4dff79d5e6102c","entry":"apply_rotary_pos_emb","repo":"FuxiaoLiu/LRV-Instruction","repo_kind":"listed","path":"MiniGPT-4/minigpt4/models/modeling_llama.py","file_url":"https://github.com/FuxiaoLiu/LRV-Instruction/blob/HEAD/MiniGPT-4/minigpt4/models/modeling_llama.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"9b4dff79d5e6102c"}},{"code_sha256_prefix":"83f3a971c12b62d4","entry":"collate_fn","repo":"FuxiaoLiu/VisualNews-Repository","repo_kind":"listed","path":"model/dataloader.py","file_url":"https://github.com/FuxiaoLiu/VisualNews-Repository/blob/HEAD/model/dataloader.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":"83f3a971c12b62d4"}},{"code_sha256_prefix":"abeed4541facd810","entry":"cuda_variable","repo":"FuxiaoLiu/VisualNews-Repository","repo_kind":"listed","path":"model/model.py","file_url":"https://github.com/FuxiaoLiu/VisualNews-Repository/blob/HEAD/model/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"abeed4541facd810"}},{"code_sha256_prefix":"4cb732f513d69dfd","entry":"disabled_train","repo":"FuxiaoLiu/LRV-Instruction","repo_kind":"listed","path":"MiniGPT-4/minigpt4/models/blip2.py","file_url":"https://github.com/FuxiaoLiu/LRV-Instruction/blob/HEAD/MiniGPT-4/minigpt4/models/blip2.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"4cb732f513d69dfd"}},{"code_sha256_prefix":"d85bcc4f59fe10b4","entry":"load_embeddings","repo":"FuxiaoLiu/VisualNews-Repository","repo_kind":"listed","path":"model/utils.py","file_url":"https://github.com/FuxiaoLiu/VisualNews-Repository/blob/HEAD/model/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":"d85bcc4f59fe10b4"}},{"code_sha256_prefix":"791c72070c0b1cfb","entry":"node_to_dict","repo":"FuxiaoLiu/LRV-Instruction","repo_kind":"listed","path":"MiniGPT-4/minigpt4/common/config.py","file_url":"https://github.com/FuxiaoLiu/LRV-Instruction/blob/HEAD/MiniGPT-4/minigpt4/common/config.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"791c72070c0b1cfb"}},{"code_sha256_prefix":"b99eea6376d1e212","entry":"rotate_half","repo":"FuxiaoLiu/LRV-Instruction","repo_kind":"listed","path":"MiniGPT-4/minigpt4/models/modeling_llama.py","file_url":"https://github.com/FuxiaoLiu/LRV-Instruction/blob/HEAD/MiniGPT-4/minigpt4/models/modeling_llama.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"b99eea6376d1e212"}},{"code_sha256_prefix":"cb33571427334815","entry":"tile","repo":"FuxiaoLiu/LRV-Instruction","repo_kind":"listed","path":"MiniGPT-4/minigpt4/models/base_model.py","file_url":"https://github.com/FuxiaoLiu/LRV-Instruction/blob/HEAD/MiniGPT-4/minigpt4/models/base_model.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"cb33571427334815"}},{"code_sha256_prefix":"0ec9fc2025c16f65","entry":"all_gather_with_grad","repo":"FuxiaoLiu/LRV-Instruction","repo_kind":"listed","path":"MiniGPT-4/minigpt4/models/base_model.py","file_url":"https://github.com/FuxiaoLiu/LRV-Instruction/blob/HEAD/MiniGPT-4/minigpt4/models/base_model.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"0ec9fc2025c16f65"}},{"code_sha256_prefix":"2def4d18e743753b","entry":"bleu","repo":"FuxiaoLiu/VisualNews-Repository","repo_kind":"listed","path":"model/model.py","file_url":"https://github.com/FuxiaoLiu/VisualNews-Repository/blob/HEAD/model/model.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":"2def4d18e743753b"}},{"code_sha256_prefix":"518df0cc5124e5f4","entry":"calculate_linear_neighbor_simi","repo":"yangyucheng000/Paper-4","repo_kind":"listed","path":"CompareExperiment/LNLP_method.py","file_url":"https://github.com/yangyucheng000/Paper-4/blob/HEAD/CompareExperiment/LNLP_method.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"518df0cc5124e5f4"}},{"code_sha256_prefix":"81305e2c0d5ef1a9","entry":"check_is_number","repo":"fuxiaoliu/mmc","repo_kind":"official","path":"Eval/utils.py","file_url":"https://github.com/fuxiaoliu/mmc/blob/HEAD/Eval/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"81305e2c0d5ef1a9"}},{"code_sha256_prefix":"8eec539bc59b1041","entry":"fast_calculate_new","repo":"yangyucheng000/Paper-4","repo_kind":"listed","path":"CompareExperiment/LNLP_method.py","file_url":"https://github.com/yangyucheng000/Paper-4/blob/HEAD/CompareExperiment/LNLP_method.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"8eec539bc59b1041"}},{"code_sha256_prefix":"50b66e6b51809672","entry":"normalize_by_divide_rowsum","repo":"yangyucheng000/Paper-4","repo_kind":"listed","path":"CompareExperiment/LNLP_method.py","file_url":"https://github.com/yangyucheng000/Paper-4/blob/HEAD/CompareExperiment/LNLP_method.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"50b66e6b51809672"}},{"code_sha256_prefix":"f487f39071cb0cac","entry":"normalize_str","repo":"fuxiaoliu/mmc","repo_kind":"official","path":"Eval/utils.py","file_url":"https://github.com/fuxiaoliu/mmc/blob/HEAD/Eval/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"f487f39071cb0cac"}},{"code_sha256_prefix":"f3018307f9301da1","entry":"parse_multi_choice_response","repo":"fuxiaoliu/mmc","repo_kind":"official","path":"Eval/utils.py","file_url":"https://github.com/fuxiaoliu/mmc/blob/HEAD/Eval/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"f3018307f9301da1"}},{"code_sha256_prefix":"4c803e3c26d895b8","entry":"sort_matrix","repo":"yangyucheng000/Paper-4","repo_kind":"listed","path":"CompareExperiment/sortscore.py","file_url":"https://github.com/yangyucheng000/Paper-4/blob/HEAD/CompareExperiment/sortscore.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"4c803e3c26d895b8"}},{"code_sha256_prefix":"770df76cea8ddf5e","entry":"translate_sentence","repo":"FuxiaoLiu/VisualNews-Repository","repo_kind":"listed","path":"model/model.py","file_url":"https://github.com/FuxiaoLiu/VisualNews-Repository/blob/HEAD/model/model.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":"770df76cea8ddf5e"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}