Papers › Large Scale Transfer Learning for Tabular Data via Language Modeling

Large Scale Transfer Learning for Tabular Data via Language Modeling

17 Jun 2024arXiv:2406.12031archive 2025-07-28

Josh Gardner, Juan C. Perdomo, Ludwig Schmidt

Tabular data -- structured, heterogeneous, spreadsheet-style data with rows and columns -- is widely used in practice across many domains. However, while recent foundation models have reduced the need for developing task-specific datasets and predictors in domains such as language modeling and computer vision, this transfer learning paradigm has not had similar impact in the tabular domain. In this work, we seek to narrow this gap and present TabuLa-8B, a language model for tabular prediction. We define a process for extracting a large, high-quality training dataset from the TabLib corpus, proposing methods for tabular data filtering and quality control. Using the resulting dataset, which comprises over 2.1B rows from over 4M unique tables, we fine-tune a Llama 3-8B large language model (LLM) for tabular data prediction (classification and binned regression) using a novel packing and attention scheme for tabular prediction. Through evaluation across a test suite of 329 datasets, we find that TabuLa-8B has zero-shot accuracy on unseen tables that is over 15 percentage points (pp) higher than random guessing, a feat that is not possible with existing state-of-the-art tabular prediction models (e.g. XGBoost, TabPFN). In the few-shot setting (1-32 shots), without any fine-tuning on the target datasets, TabuLa-8B is 5-15 pp more accurate than XGBoost and TabPFN models that are explicitly trained on equal, or even up to 16x more data. We release our model, code, and data along with the publication of this paper.

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 15 code samples harvested from 2 repositories linked to this paper: 13 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 10 where Syntology's instrument failed) · 2 unverified. Where Syntology's instrument failed: 8 where our contract draft was wrong; 2 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 15 samples from 2 repositories, 13 ran (3 with no instrument failure; 10 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 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

mlfoundations/rtfm officialmentioned in papermentioned on GitHubpytorchMITSyntology: 7 samples, 5 ran (3 instrument-failed) · 2 unverified report
mlfoundations/tabliblib officialmentioned in paperMITSyntology: 8 samples, 8 ran (7 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

15 samples harvested: 13 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 10 where Syntology's instrument failed) · 2 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · honoured contract
8ran · our draft was wrong
2ran; the contract check could not run
2ran
2unverified

Licence: 0 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 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.

mlfoundations/rtfm official repository 7 samples, 5 ran (3 instrument-failed) · 2 unverified
batch_to_xpu rtfm/torch_utils.py ran · our draft was wrong MIT (permissive) · 1af054b95295710e · report fixture: signature batch:dict/0/? · returned dict · level recorded 2026-09-24
example_ids_to_attention_mask rtfm/data.py ran; the contract check could not run (RAISES) MIT (permissive) · 74807ffb0cddac16 · report fixture: signature example_ids:list/1/int · returned ndarray · level recorded 2026-09-24
get_categorical_idxs rtfm/tree_baselines.py ran · honoured contract MIT (permissive) · cd4c51c2326006e9 · report fixture: signature df:DataFrame/0/? · returned list · level recorded 2026-09-24
get_latest_checkpoint in 13 papers rtfm/utils.py ran · our draft was wrong MIT (permissive) · ba26941c52b7f85a · report fixture: signature dirpath:str/0/str · returned str · level recorded 2026-09-24
load_model_from_checkpoint rtfm/train_utils.py ran MIT (permissive) · d718f67e89480b5b · report fixture: signature model:callable/0/?, ckpt_dir:str/0/str · returned tuple · level recorded 2026-09-24
bool_cols_to_categorical rtfm/tree_baselines.py unverified MIT (permissive) · 5326e55483a6717d · report
prepare_4d_attention_mask rtfm/data.py unverified MIT (permissive) · 7d1cac2a511468ae · report
mlfoundations/tabliblib official repository 8 samples, 8 ran (7 instrument-failed) · 0 unverified
add_content_hash tabliblib/mappers.py ran · our draft was wrong MIT (permissive) · 4beae4af6e4059ec · report fixture: signature row:dict/0/? · returned dict · level recorded 2026-09-24
arrow_to_pandas_safe tabliblib/io.py ran · our draft was wrong MIT (permissive) · 5af725e76bd12300 · report fixture: signature t:Table/0/?, raise_on_error:bool/0/bool · returned DataFrame · level recorded 2026-09-24
drop_duplicates tabliblib/mappers.py ran MIT (permissive) · 0ad24980bda6f6e4 · report fixture: signature batch:dict/0/?, key:str/0/str, sort_by:str/0/str · returned dict · level recorded 2026-09-24
find_covering_set tabliblib/dedup_utils.py ran · our draft was wrong MIT (permissive) · 4767aa5be418958c · report fixture: signature file_string_tuples:list/1/tuple · returned list · level recorded 2026-09-24
generate_random_dates tabliblib/summarizers.py ran · our draft was wrong MIT (permissive) · 8d749d50f25dd3c2 · report fixture: signature start_date:datetime/0/?, end_date:datetime/0/? · returned list · level recorded 2026-09-24
path_to_str in 5 papers tabliblib/dedup_utils.py ran · our draft was wrong fingerprinted MIT (permissive) · 39954605fabc6757 · report fixture: signature path:str/0/str · returned str · level recorded 2026-09-24
sample_columns_if_needed tabliblib/io.py ran; the contract check could not run (RAISES) MIT (permissive) · 02efcf6df251ab61 · report fixture: signature df:DataFrame/0/?, max_cols:int/0/int · returned DataFrame · level recorded 2026-09-24
write_arrow_bytes tabliblib/io.py ran · our draft was wrong MIT (permissive) · 61bc6ff6d93f37c7 · report fixture: signature df:DataFrame/0/? · returned bytes · level recorded 2026-09-24

Tasks

Language ModelingLanguage ModellingLarge Language ModelPredictionTransfer Learning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

AttentionLLaMASoftmaxTABPFN

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