Papers › TabSQLify: Enhancing Reasoning Capabilities of LLMs Through Table Decomposition

TabSQLify: Enhancing Reasoning Capabilities of LLMs Through Table Decomposition

15 Apr 2024arXiv:2404.10150archive 2025-07-28

Md Mahadi Hasan Nahid, Davood Rafiei

Table reasoning is a challenging task that requires understanding both natural language questions and structured tabular data. Large language models (LLMs) have shown impressive capabilities in natural language understanding and generation, but they often struggle with large tables due to their limited input length. In this paper, we propose TabSQLify, a novel method that leverages text-to-SQL generation to decompose tables into smaller and relevant sub-tables, containing only essential information for answering questions or verifying statements, before performing the reasoning task. In our comprehensive evaluation on four challenging datasets, our approach demonstrates comparable or superior performance compared to prevailing methods reliant on full tables as input. Moreover, our method can reduce the input context length significantly, making it more scalable and efficient for large-scale table reasoning applications. Our method performs remarkably well on the WikiTQ benchmark, achieving an accuracy of 64.7%. Additionally, on the TabFact benchmark, it achieves a high accuracy of 79.5%. These results surpass other LLM-based baseline models on gpt-3.5-turbo (chatgpt). TabSQLify can reduce the table size significantly alleviating the computational load on LLMs when handling large tables without compromising performance.

PaperPDFCodeCode Syntology ranMethod as code

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 15 code samples harvested from 1 repository linked to this paper: 7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 6 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 8 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 15 samples from 1 repository, 7 ran (6 with no instrument failure; 1 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

No sample is linked to this paper from 1 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

mahadi-nahid/tabsqlify officialmentioned in paperSyntology: 15 samples, 7 ran (1 instrument-failed) · 8 unverified report
nikhilsab/h-star mentioned on GitHubSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to H-STAR: LLM-driven Hybrid SQL-Text Adaptive Reasoning on Tables (arXiv:2407.05952; that paper's own run record: 3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

15 samples harvested: 7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 6 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 8 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

6ran · honoured contract
1ran · our draft was wrong
8unverified

Licence: 15 of the 15 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from mahadi-nahid/tabsqlify. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: 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. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

mahadi-nahid/tabsqlify official repository 15 samples, 7 ran (1 instrument-failed) · 8 unverified
parse_limit utils/extraction_from_sql.py ran · honoured contract fingerprinted no licence file found · pointer only · 38e4069e5b096cec · report fixture: signature toks:list/1/str, start_idx:int/0/int · returned int · level recorded 2026-09-24
parse_order_by utils/extraction_from_sql.py ran · honoured contract no licence file found · pointer only · cb44b522e20def3b · report fixture: signature toks:list/1/str, start_idx:int/0/int, tables_with_alias:dict/0/?, schema:dict/0/?, default_tables:list/1/str · returned int · level recorded 2026-09-24
parse_select utils/extraction_from_sql.py ran · honoured contract no licence file found · pointer only · 651dbafae2c91680 · report fixture: signature toks:list/1/str, start_idx:int/0/int, tables_with_alias:dict/0/?, schema:dict/0/?, default_tables:list/1/str · returned int · level recorded 2026-09-24
parse_table_unit utils/extraction_from_sql.py ran · our draft was wrong no licence file found · pointer only · 218726c6afc81470 · report fixture: signature toks:list/1/str, start_idx:int/0/int, tables_with_alias:dict/0/? · returned tuple · level recorded 2026-09-24
parse_value in 7 papers utils/extraction_from_sql.py ran · honoured contract no licence file found · pointer only · 20e6bf91068797e9 · report fixture: signature toks:list/1/str, start_idx:int/0/int, tables_with_alias:dict/0/?, schema:dict/0/?, default_tables:list/1/str · returned int · level recorded 2026-09-24
parse_where utils/extraction_from_sql.py ran · honoured contract no licence file found · pointer only · 36cb09c5018fd5f4 · report fixture: signature toks:list/1/str, start_idx:int/0/int, tables_with_alias:dict/0/?, schema:dict/0/?, default_tables:list/1/str · returned int · level recorded 2026-09-24
skip_semicolon utils/extraction_from_sql.py ran · honoured contract fingerprinted no licence file found · pointer only · 7523ecfde4aa5252 · report fixture: signature toks:list/1/str, start_idx:int/0/int · returned int · level recorded 2026-09-22
parse_col utils/extraction_from_sql.py unverified no licence file found · pointer only · e02203bc18aaec5e · report
parse_col_unit utils/extraction_from_sql.py unverified no licence file found · pointer only · 1cf8d3a86aefa5ca · report
parse_condition utils/extraction_from_sql.py unverified no licence file found · pointer only · 50401742feeda9e6 · report
parse_from utils/extraction_from_sql.py unverified no licence file found · pointer only · 1ff435f71c45515d · report
parse_group_by utils/extraction_from_sql.py unverified no licence file found · pointer only · b0f4816227ae33c5 · report
parse_having utils/extraction_from_sql.py unverified no licence file found · pointer only · 74e1de748313ae30 · report
parse_sql utils/extraction_from_sql.py unverified no licence file found · pointer only · 4530fd8535c9d726 · report
parse_val_unit utils/extraction_from_sql.py unverified no licence file found · pointer only · 412bddc33084d837 · report

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it.

1 assembly on this paper: 1 harvested, 0 generated.

harvested Assembly for TabSQLify (graph method: TabSQLify). 15 bricks; individually on a fixture: 7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 6 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 8 unverified. The assembly has not been run end-to-end.

  1. parse_sql entry · level 0 · unverified · 4530fd8535c9d726
  2. parse_from helper · level 0 · unverified · 1ff435f71c45515d
  3. parse_group_by helper · level 0 · unverified · b0f4816227ae33c5
  4. parse_having helper · level 0 · unverified · 74e1de748313ae30
  5. parse_limit helper · level 1 · ran · honoured contract · 38e4069e5b096cec
  6. parse_order_by helper · level 1 · ran · honoured contract · cb44b522e20def3b
  7. parse_select helper · level 1 · ran · honoured contract · 651dbafae2c91680
  8. parse_where helper · level 1 · ran · honoured contract · 36cb09c5018fd5f4
  9. skip_semicolon helper · level 1 · ran · honoured contract · 7523ecfde4aa5252
  10. parse_condition helper · level 0 · unverified · 50401742feeda9e6
  11. parse_table_unit helper · level 1 · ran · our draft was wrong · 218726c6afc81470
  12. parse_col_unit helper · level 0 · unverified · 1cf8d3a86aefa5ca
  13. parse_val_unit helper · level 0 · unverified · 412bddc33084d837
  14. parse_value helper · level 1 · ran · honoured contract · 20e6bf91068797e9
  15. parse_col helper · level 0 · unverified · e02203bc18aaec5e

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2404.10150") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Natural Language UnderstandingQuestion AnsweringSemantic ParsingTable-based Fact VerificationText to SQLText-To-SQL

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Question Answering WikiSQL TabSQLify Exact Match (EM) 82.84 #2 of 2 Archive leaderboard report
Question Answering WikiTableQuestions TabSQLify (col+row) Accuracy (Test) 64.7 #2 of 2 Archive leaderboard report
Semantic Parsing WikiTableQuestions TabSQLify (col+row) Accuracy (Test) 64.7 #12 of 22 Archive leaderboard report
Table-based Fact Verification TabFact TabSQLify (col+row) Test 79.5 #12 of 15 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections