{"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/tablegpt2-a-large-multimodal-model-with","title":"TableGPT2: A Large Multimodal Model with Tabular Data Integration","arxiv_id":"2411.02059","date":"2024-11-04","proceeding":null,"authors":["Aofeng Su","Aowen Wang","Chao Ye","Chen Zhou","Ga Zhang","Gang Chen","Guangcheng Zhu","Haobo Wang","Haokai Xu","Hao Chen","Haoze Li","Haoxuan Lan","Jiaming Tian","Jing Yuan","Junbo Zhao","Junlin Zhou","Kaizhe Shou","Liangyu Zha","Lin Long","Liyao Li","Pengzuo Wu","Qi Zhang","Qingyi Huang","Saisai Yang","Tao Zhang","Wentao Ye","Wufang Zhu","Xiaomeng Hu","Xijun Gu","Xinjie Sun","Xiang Li","Yuhang Yang","Zhiqing Xiao"],"abstract":"The emergence of models like GPTs, Claude, LLaMA, and Qwen has reshaped AI applications, presenting vast new opportunities across industries. Yet, the integration of tabular data remains notably underdeveloped, despite its foundational role in numerous real-world domains. This gap is critical for three main reasons. First, database or data warehouse data integration is essential for advanced applications; second, the vast and largely untapped resource of tabular data offers immense potential for analysis; and third, the business intelligence domain specifically demands adaptable, precise solutions that many current LLMs may struggle to provide. In response, we introduce TableGPT2, a model rigorously pre-trained and fine-tuned with over 593.8K tables and 2.36M high-quality query-table-output tuples, a scale of table-related data unprecedented in prior research. This extensive training enables TableGPT2 to excel in table-centric tasks while maintaining strong general language and coding abilities. One of TableGPT2's key innovations is its novel table encoder, specifically designed to capture schema-level and cell-level information. This encoder strengthens the model's ability to handle ambiguous queries, missing column names, and irregular tables commonly encountered in real-world applications. Similar to visual language models, this pioneering approach integrates with the decoder to form a robust large multimodal model. We believe the results are compelling: over 23 benchmarking metrics, TableGPT2 achieves an average performance improvement of 35.20% in the 7B model and 49.32% in the 72B model over prior benchmark-neutral LLMs, with robust general-purpose capabilities intact.","url_abs":"https://arxiv.org/abs/2411.02059v3","url_pdf":"https://arxiv.org/pdf/2411.02059v3.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":"tablegpt2-a-large-multimodal-model-with","repo_url":"https://github.com/tablegpt/tablegpt-agent","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"benchmarking","task_name":"Benchmarking"},{"task_slug":"data-integration","task_name":"Data Integration"}],"methods":[{"method_slug":"llama","method_name":"LLaMA"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2411.02059","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.02059"}},"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/tablegpt/tablegpt-agent","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"unverified":4},"by_repo_kind":{"official":{"samples":4,"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":0,"samples":[{"code_sha256_prefix":"40b543d80d4d561e","entry":"file_extension","repo":"tablegpt/tablegpt-agent","repo_kind":"official","path":"src/tablegpt/utils.py","file_url":"https://github.com/tablegpt/tablegpt-agent/blob/HEAD/src/tablegpt/utils.py","link_basis":"first_harvest_node","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":"40b543d80d4d561e"}},{"code_sha256_prefix":"9b024751e4c0cdbe","entry":"is_split","repo":"tablegpt/tablegpt-agent","repo_kind":"official","path":"src/tablegpt/agent/file_reading/data_normalizer.py","file_url":"https://github.com/tablegpt/tablegpt-agent/blob/HEAD/src/tablegpt/agent/file_reading/data_normalizer.py","link_basis":"first_harvest_node","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":"9b024751e4c0cdbe"}},{"code_sha256_prefix":"47424b85db67d508","entry":"process_content","repo":"tablegpt/tablegpt-agent","repo_kind":"official","path":"src/tablegpt/tools.py","file_url":"https://github.com/tablegpt/tablegpt-agent/blob/HEAD/src/tablegpt/tools.py","link_basis":"first_harvest_node","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":"47424b85db67d508"}},{"code_sha256_prefix":"3bc3d05d0cb64192","entry":"seq_to_md","repo":"tablegpt/tablegpt-agent","repo_kind":"official","path":"src/tablegpt/agent/file_reading/data_normalizer.py","file_url":"https://github.com/tablegpt/tablegpt-agent/blob/HEAD/src/tablegpt/agent/file_reading/data_normalizer.py","link_basis":"first_harvest_node","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":"3bc3d05d0cb64192"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}