{"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/tap4llm-table-provider-on-sampling-augmenting","title":"TAP4LLM: Table Provider on Sampling, Augmenting, and Packing Semi-structured Data for Large Language Model Reasoning","arxiv_id":"2312.09039","date":"2023-12-14","proceeding":null,"authors":["Yuan Sui","Jiaru Zou","Mengyu Zhou","Xinyi He","Lun Du","Shi Han","Dongmei Zhang"],"abstract":"Table reasoning tasks have shown remarkable progress with the development of large language models (LLMs), which involve interpreting and drawing conclusions from tabular data based on natural language (NL) questions. Existing solutions mainly tested on smaller tables face scalability issues and struggle with complex queries due to incomplete or dispersed data across different table sections. To alleviate these challenges, we propose TAP4LLM as a versatile pre-processor suite for leveraging LLMs in table-based tasks effectively. It covers several distinct components: (1) table sampling to decompose large tables into manageable sub-tables based on query semantics, (2) table augmentation to enhance tables with additional knowledge from external sources or models, and (3) table packing & serialization to convert tables into various formats suitable for LLMs' understanding. In each module, we design and compare several common methods under various usage scenarios, aiming to shed light on the best practices for leveraging LLMs for table-reasoning tasks. Our experiments show that our method improves LLMs' reasoning capabilities in various tabular tasks and enhances the interaction between LLMs and tabular data by employing effective pre-processing.","url_abs":"https://arxiv.org/abs/2312.09039v3","url_pdf":"https://arxiv.org/pdf/2312.09039v3.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":"tap4llm-table-provider-on-sampling-augmenting","repo_url":"https://github.com/Y-Sui/GPT4Table","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"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":"semantic-similarity","task_name":"Semantic Similarity"},{"task_slug":"semantic-textual-similarity","task_name":"Semantic Textual Similarity"}],"methods":[{"method_slug":"speed","method_name":"SPEED"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2312.09039","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.09039"}},"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/Y-Sui/GPT4Table","reach":{"status":"ok"}}],"summary":{"ran":12,"ran_honours":1,"unverified":1},"by_repo_kind":{"listed":{"samples":14,"ran":13,"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":14,"samples":[{"code_sha256_prefix":"79f3ecb504ea2b1e","entry":"exact_match_score","repo":"Y-Sui/GPT4Table","repo_kind":"listed","path":"table_meets_llm/eval/evaluate_benchmark.py","file_url":"https://github.com/Y-Sui/GPT4Table/blob/HEAD/table_meets_llm/eval/evaluate_benchmark.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":"79f3ecb504ea2b1e"}},{"code_sha256_prefix":"1277e6201cadd4d1","entry":"f1_metric","repo":"Y-Sui/GPT4Table","repo_kind":"listed","path":"table_meets_llm/eval/evaluate_individual_tasks.py","file_url":"https://github.com/Y-Sui/GPT4Table/blob/HEAD/table_meets_llm/eval/evaluate_individual_tasks.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":"1277e6201cadd4d1"}},{"code_sha256_prefix":"1ab36f0f7c198f2e","entry":"flatten_list","repo":"Y-Sui/GPT4Table","repo_kind":"listed","path":"table_meets_llm/eval/evaluate_benchmark.py","file_url":"https://github.com/Y-Sui/GPT4Table/blob/HEAD/table_meets_llm/eval/evaluate_benchmark.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":"1ab36f0f7c198f2e"}},{"code_sha256_prefix":"e6d8b0f710a525a0","entry":"format_mapping_func","repo":"Y-Sui/GPT4Table","repo_kind":"listed","path":"table_meets_llm/utils/evaluate_tools.py","file_url":"https://github.com/Y-Sui/GPT4Table/blob/HEAD/table_meets_llm/utils/evaluate_tools.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":"e6d8b0f710a525a0"}},{"code_sha256_prefix":"1ffe070dc06e5e70","entry":"get_heuristics","repo":"Y-Sui/GPT4Table","repo_kind":"listed","path":"table_meets_llm/main/config.py","file_url":"https://github.com/Y-Sui/GPT4Table/blob/HEAD/table_meets_llm/main/config.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":"1ffe070dc06e5e70"}},{"code_sha256_prefix":"27128d289021da5a","entry":"get_list_id","repo":"Y-Sui/GPT4Table","repo_kind":"listed","path":"table_meets_llm/dataset_collection/feverous.py","file_url":"https://github.com/Y-Sui/GPT4Table/blob/HEAD/table_meets_llm/dataset_collection/feverous.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":"27128d289021da5a"}},{"code_sha256_prefix":"ea710e58e85aeea2","entry":"get_requests","repo":"Y-Sui/GPT4Table","repo_kind":"listed","path":"table_meets_llm/main/config.py","file_url":"https://github.com/Y-Sui/GPT4Table/blob/HEAD/table_meets_llm/main/config.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":"ea710e58e85aeea2"}},{"code_sha256_prefix":"f1cc796d436c04ca","entry":"get_table_id","repo":"Y-Sui/GPT4Table","repo_kind":"listed","path":"table_meets_llm/dataset_collection/feverous.py","file_url":"https://github.com/Y-Sui/GPT4Table/blob/HEAD/table_meets_llm/dataset_collection/feverous.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":"f1cc796d436c04ca"}},{"code_sha256_prefix":"bcbe65db799d70f9","entry":"load_results_from_json","repo":"Y-Sui/GPT4Table","repo_kind":"listed","path":"table_meets_llm/utils/evaluate_tools.py","file_url":"https://github.com/Y-Sui/GPT4Table/blob/HEAD/table_meets_llm/utils/evaluate_tools.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":"bcbe65db799d70f9"}},{"code_sha256_prefix":"9273c95ad6ca5625","entry":"reformat_sequence","repo":"Y-Sui/GPT4Table","repo_kind":"listed","path":"table_meets_llm/eval/evaluate_individual_tasks.py","file_url":"https://github.com/Y-Sui/GPT4Table/blob/HEAD/table_meets_llm/eval/evaluate_individual_tasks.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":"9273c95ad6ca5625"}},{"code_sha256_prefix":"62f798e358e0b796","entry":"retrieve_unique_cell_element","repo":"Y-Sui/GPT4Table","repo_kind":"listed","path":"table_meets_llm/main/unified_benchmark_generator.py","file_url":"https://github.com/Y-Sui/GPT4Table/blob/HEAD/table_meets_llm/main/unified_benchmark_generator.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":"62f798e358e0b796"}},{"code_sha256_prefix":"47b8f3a12d99e266","entry":"retrieve_unique_row_element","repo":"Y-Sui/GPT4Table","repo_kind":"listed","path":"table_meets_llm/main/unified_benchmark_generator.py","file_url":"https://github.com/Y-Sui/GPT4Table/blob/HEAD/table_meets_llm/main/unified_benchmark_generator.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":"47b8f3a12d99e266"}},{"code_sha256_prefix":"a09b5bf35fd2d8ab","entry":"string_similar","repo":"Y-Sui/GPT4Table","repo_kind":"listed","path":"table_meets_llm/eval/evaluate_individual_tasks.py","file_url":"https://github.com/Y-Sui/GPT4Table/blob/HEAD/table_meets_llm/eval/evaluate_individual_tasks.py","link_basis":"plan_row","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"a09b5bf35fd2d8ab"}},{"code_sha256_prefix":"aa0ed7b47981763f","entry":"get_keys","repo":"Y-Sui/GPT4Table","repo_kind":"listed","path":"table_meets_llm/main/unified_babel_convertor.py","file_url":"https://github.com/Y-Sui/GPT4Table/blob/HEAD/table_meets_llm/main/unified_babel_convertor.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":"aa0ed7b47981763f"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}