Papers › Optimization Techniques for Unsupervised Complex Table Reasoning via Self-Training Framework

Optimization Techniques for Unsupervised Complex Table Reasoning via Self-Training Framework

20 Dec 2022arXiv:2212.10097archive 2025-07-28

Zhenyu Li, Xiuxing Li, Sunqi Fan, Jianyong Wang

Structured tabular data is a fundamental data type in numerous fields, and the capacity to reason over tables is crucial for answering questions and validating hypotheses. However, constructing labeled data for complex reasoning tasks is labor intensive, and the quantity of annotated data remains insufficient to support the intricate demands of real-world applications. To address the insufficient annotation challenge, we present a self-training framework for unsupervised complex tabular reasoning (UCTR-ST) by generating diverse synthetic data with complex logic. Specifically, UCTR-ST incorporates several essential techniques: we aggregate diverse programs and execute them on tables based on a "Program-Management" component, and we bridge the gap between programs and text with a powerful "Program-Transformation" module that generates natural language sentences with complex logic. Furthermore, we optimize the procedure using a "Table-Text Manipulator" to handle joint table-text reasoning scenarios. The entire framework utilizes self-training techniques to leverage the unlabeled training data, which results in significant performance improvements when tested on real-world data. Experimental results demonstrate that UCTRST achieves above 90% of the supervised model performance on different tasks and domains, reducing the dependence on manual annotation. Additionally, our approach can serve as a data augmentation technique, significantly boosting the performance of supervised models in low-resourced domains.

PaperPDFCodeCode Syntology ran

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 20 code samples harvested from 2 repositories linked to this paper: 17 ran (of which 0 constructed an object rather than computing a result; 17 with no instrument failure: 0 honoured, 0 violated, 17 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: official repository: 20 samples from 2 repositories, 17 ran (17 with no instrument failure; 0 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.

Levels written on 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

leezythu/uctr officialmentioned in paperjaxMITSyntology: 16 samples, 13 ran (0 instrument-failed) · 3 unverified report
leezythu/uctr-st officialmentioned in paperjaxMITSyntology: 4 samples, 4 ran (0 instrument-failed) · 0 unverified 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.

Code Syntology ran Syntology

20 samples harvested: 17 ran (of which 0 constructed an object rather than computing a result; 17 with no instrument failure: 0 honoured, 0 violated, 17 with no contract checked; 0 where Syntology's instrument failed) · 3 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.

17ran
3unverified

Licence: 0 of the 20 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 2 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “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. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

leezythu/uctr official repository 16 samples, 13 ran (0 instrument-failed) · 3 unverified
ds_arg FEVEROUS/process_program.py ran MIT (permissive) · b75be4391719a2b0 · report fixture: signature logic:dict/0/?, all:list/1/empty, pos_d:dict/0/? · returned str · level recorded 2026-09-25
find_index in 8 papers FEVEROUS/fill_in_template.py ran MIT (permissive) · 534cdb9a35bb5f05 · report fixture: signature val:int/0/int, table:list/1/list · returned tuple · level recorded 2026-09-25
find_num TAT-QA/finqa/collect_data.py ran fingerprinted MIT (permissive) · 18e12d28c390eca0 · report fixture: signature program:str/0/str · returned list · level recorded 2026-09-25
find_pos FEVEROUS/process_program.py ran MIT (permissive) · 4f0aabb25ef5e927 · report fixture: signature rows:list/1/list · returned dict · level recorded 2026-09-25
find_pos FEVEROUS/syn.py ran MIT (permissive) · a8deec34bf20a0a4 · report fixture: signature table:dict/0/? · returned dict · level recorded 2026-09-25
fuzzy_compare_filter FEVEROUS/execution/APIs.py ran MIT (permissive) · 9b7f0f8a8a9d658e · report fixture: signature t:DataFrame/0/?, col:str/0/str, val:str/0/str, type:str/0/str · returned DataFrame · level recorded 2026-09-25
fuzzy_match_filter FEVEROUS/execution/APIs.py ran MIT (permissive) · bd791c82a8efe829 · report fixture: signature t:DataFrame/0/?, col:str/0/str, val:str/0/str, negate:bool/0/bool · returned DataFrame · level recorded 2026-09-25
get_description TAT-QA/finqa/collect_data.py ran MIT (permissive) · e625b89f3bb8669a · report fixture: signature num:str/0/str, table:list/1/list · returned str · level recorded 2026-09-25
get_evidence FEVEROUS/fill_in_template.py ran MIT (permissive) · b3ccf463e4486dce · report fixture: signature feed_dict:dict/0/?, must_have:list/1/str, type:str/0/str, table_index:int/0/int, doc:str/0/str, table:list/1/list, is_header:list/1/list · returned list · level recorded 2026-09-25
locate_num TAT-QA/finqa/collect_data.py ran MIT (permissive) · a79f0ace7e53331c · report fixture: signature num:int/0/int, table:list/1/list · returned tuple · level recorded 2026-09-25
normalize in 638 papers
census: 70 implementations from 82 papers, 51 distinct outputs across 11 buckets, one shared input per bucket
FEVEROUS/syn.py ran MIT (permissive) · c4ae14071abdbcdf · report fixture: signature row:MockRow/0/? · returned list · level recorded 2026-09-25
obj_compare FEVEROUS/execution/APIs.py ran MIT (permissive) · f36c3eba21146e55 · report fixture: signature num1:float/0/float, num2:float/0/float, round:bool/0/bool, type:str/0/str · returned bool · level recorded 2026-09-25
paraphrase FEVEROUS/process_program.py ran MIT (permissive) · 3941e0c5c9a3493d · report fixture: signature func:str/0/str · returned str · level recorded 2026-09-25
execute_all FEVEROUS/execution/execute.py unverified MIT (permissive) · bb7c3358b37dc877 · report
gen_feed FEVEROUS/syn.py unverified MIT (permissive) · 59e65dbe081b83ae · report
gen_feed SEM-TAB-FACTS/syn.py unverified MIT (permissive) · 0f626cad0a001441 · report
leezythu/uctr-st official repository 4 samples, 4 ran (0 instrument-failed) · 0 unverified
get_mapping in 5 papers TAT-QA/generate_pseudo.py ran MIT (permissive) · defe43aaba4c6447 · report fixture: signature table:list/1/list, para:list/1/dict, facts:list/1/int · returned dict · level recorded 2026-09-25
get_para_mapping TAT-QA/generate_pseudo.py ran MIT (permissive) · a4ec9baf2fc7a4f5 · report fixture: signature para:list/1/dict, fact:str/0/str · returned tuple · level recorded 2026-09-25
get_table_mapping TAT-QA/generate_pseudo.py ran MIT (permissive) · ce5896bb3ae606e2 · report fixture: signature table:list/1/list, fact:int/0/int · returned list · level recorded 2026-09-25
normalize in 638 papers
census: 70 implementations from 82 papers, 51 distinct outputs across 11 buckets, one shared input per bucket
SEM-TAB-FACTS/syn.py ran MIT (permissive) · cfb7267da4dc4f92 · report fixture: signature table:list/1/list · returned list · level recorded 2026-09-25

Tasks

Data AugmentationFact VerificationQuestion Answering

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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