{"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/rethinking-tabular-data-understanding-with","title":"Rethinking Tabular Data Understanding with Large Language Models","arxiv_id":"2312.16702","date":"2023-12-27","proceeding":null,"authors":["Tianyang Liu","Fei Wang","Muhao Chen"],"abstract":"Large Language Models (LLMs) have shown to be capable of various tasks, yet their capability in interpreting and reasoning over tabular data remains an underexplored area. In this context, this study investigates from three core perspectives: the robustness of LLMs to structural perturbations in tables, the comparative analysis of textual and symbolic reasoning on tables, and the potential of boosting model performance through the aggregation of multiple reasoning pathways. We discover that structural variance of tables presenting the same content reveals a notable performance decline, particularly in symbolic reasoning tasks. This prompts the proposal of a method for table structure normalization. Moreover, textual reasoning slightly edges out symbolic reasoning, and a detailed error analysis reveals that each exhibits different strengths depending on the specific tasks. Notably, the aggregation of textual and symbolic reasoning pathways, bolstered by a mix self-consistency mechanism, resulted in achieving SOTA performance, with an accuracy of 73.6% on WIKITABLEQUESTIONS, representing a substantial advancement over previous existing table processing paradigms of LLMs.","url_abs":"https://arxiv.org/abs/2312.16702v1","url_pdf":"https://arxiv.org/pdf/2312.16702v1.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":"rethinking-tabular-data-understanding-with","repo_url":"https://github.com/Leolty/tablellm","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"semantic-parsing","task_name":"Semantic Parsing"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/semantic-parsing-on-wikitablequestions","task":"Semantic Parsing","dataset":"WikiTableQuestions","model":"Mix SC","rank_in_archive_order":4,"of":22,"metrics":{"Accuracy (Dev)":"/","Accuracy (Test)":"73.6"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2312.16702","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.16702"}},"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/Leolty/tablellm","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":10,"unverified":1},"by_repo_kind":{"official":{"samples":11,"ran":10,"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":"b8b021484ec64f77","entry":"best_match_based_on_content","repo":"Leolty/tablellm","repo_kind":"official","path":"utils/table.py","file_url":"https://github.com/Leolty/tablellm/blob/HEAD/utils/table.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"b8b021484ec64f77"}},{"code_sha256_prefix":"488db90e1ef07f73","entry":"construct_markdown_table","repo":"Leolty/tablellm","repo_kind":"official","path":"utils/data.py","file_url":"https://github.com/Leolty/tablellm/blob/HEAD/utils/data.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"488db90e1ef07f73"}},{"code_sha256_prefix":"f4e20da00a5d2f24","entry":"flatten","repo":"Leolty/tablellm","repo_kind":"official","path":"evaluate.py","file_url":"https://github.com/Leolty/tablellm/blob/HEAD/evaluate.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"f4e20da00a5d2f24"}},{"code_sha256_prefix":"0cf45bc29c09c932","entry":"get_cot_prompt","repo":"Leolty/tablellm","repo_kind":"official","path":"run_helper.py","file_url":"https://github.com/Leolty/tablellm/blob/HEAD/run_helper.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"0cf45bc29c09c932"}},{"code_sha256_prefix":"a6475c2b07a6ec20","entry":"load_dataset","repo":"Leolty/tablellm","repo_kind":"official","path":"run_helper.py","file_url":"https://github.com/Leolty/tablellm/blob/HEAD/run_helper.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"a6475c2b07a6ec20"}},{"code_sha256_prefix":"1925013cb0ab7c9b","entry":"markdown_to_df","repo":"Leolty/tablellm","repo_kind":"official","path":"utils/execute.py","file_url":"https://github.com/Leolty/tablellm/blob/HEAD/utils/execute.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"1925013cb0ab7c9b"}},{"code_sha256_prefix":"c905653bda7ccc66","entry":"print_partial_markdown","repo":"Leolty/tablellm","repo_kind":"official","path":"utils/data.py","file_url":"https://github.com/Leolty/tablellm/blob/HEAD/utils/data.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"c905653bda7ccc66"}},{"code_sha256_prefix":"050b33c679b5e164","entry":"print_partial_markdown","repo":"Leolty/tablellm","repo_kind":"official","path":"utils/execute.py","file_url":"https://github.com/Leolty/tablellm/blob/HEAD/utils/execute.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"050b33c679b5e164"}},{"code_sha256_prefix":"f8e49cb5d1919217","entry":"remove_merged_suffixes","repo":"Leolty/tablellm","repo_kind":"official","path":"utils/execute.py","file_url":"https://github.com/Leolty/tablellm/blob/HEAD/utils/execute.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"f8e49cb5d1919217"}},{"code_sha256_prefix":"91e307626f8b6a11","entry":"transpose","repo":"Leolty/tablellm","repo_kind":"official","path":"utils/table.py","file_url":"https://github.com/Leolty/tablellm/blob/HEAD/utils/table.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"91e307626f8b6a11"}},{"code_sha256_prefix":"c0044887a847001b","entry":"load_results","repo":"Leolty/tablellm","repo_kind":"official","path":"evaluate.py","file_url":"https://github.com/Leolty/tablellm/blob/HEAD/evaluate.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":"c0044887a847001b"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}