TabGemma: Text-Based Tabular ICL via LLM using Continued Pretraining and Retrieval

• URL: http://arxiv.org/abs/2511.03570v1
• Date: Wed, 05 Nov 2025 15:51:03 GMT
• Title: TabGemma: Text-Based Tabular ICL via LLM using Continued Pretraining and Retrieval
• Authors: Günther Schindler, Maximilian Schambach, Michael Medek, Sam Thelin,
• Abstract summary: We introduce TabGemma, a schema-agnostic in-context learner that treats rows as sequences.<n>For inference, we use a compact n-gram-based retrieval to select informative exemplars that fit within a 128k-token window.<n>For regression, it is competitive at small sample sizes but trails conventional approaches as data grows.
• Score: 1.4995278030955144
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We study LLMs for tabular prediction with mixed text, numeric, and categorical fields. We introduce TabGemma, a schema-agnostic in-context learner that treats rows as sequences and tackles two practical hurdles when adapting pretrained LLMs for tabular predictions: unstable numeric tokenization and limited context size. We propose to canonicalize numbers via signed scientific notation and continue pretraining of a 12B Gemma 3 model with a target imputation objective using a large-scale real world dataset. For inference, we use a compact n-gram-based retrieval to select informative exemplars that fit within a 128k-token window. On semantically rich benchmarks, TabGemma establishes a new state of the art on classification across low- and high-data regimes and improves monotonically with more context rows. For regression, it is competitive at small sample sizes but trails conventional approaches as data grows. Our results show that LLMs can be effective tabular in-context learners on highly semantic tasks when paired with dedicated numeric handling and context retrieval, while motivating further advances in numeric modeling and long-context scaling.

Related papers

• Training Large Recommendation Models via Graph-Language Token Alignment [53.3142545812349]
  We propose a novel framework to train Large Recommendation models via Graph-Language Token Alignment.<n>By aligning item and user nodes from the interaction graph with pretrained LLM tokens, GLTA effectively leverages the reasoning abilities of LLMs.<n> Furthermore, we introduce Graph-Language Logits Matching (GLLM) to optimize token alignment for end-to-end item prediction.
  arXiv  Detail & Related papers  (2025-02-26T02:19:10Z)
• TabGen-ICL: Residual-Aware In-Context Example Selection for Tabular Data Generation [38.08438831075632]
  TabGen-ICL operates iteratively, retrieving a subset of real samples that represent the residual between currently generated samples and true data distributions.<n>Experiments on five real-world datasets demonstrate that TabGen-ICL significantly outperforms the random selection strategy.
  arXiv  Detail & Related papers  (2025-02-23T02:51:58Z)
• Scalable In-Context Learning on Tabular Data via Retrieval-Augmented Large Language Models [15.603556124006479]
  We propose retrieval-augmented language models for scalable TabICL.<n>Our approach incorporates a customized retrieval module, combined with retrieval-guided instruction-tuning for LLMs.<n>This enables LLMs to effectively leverage larger datasets, achieving significantly improved performance across 69 widely recognized datasets.
  arXiv  Detail & Related papers  (2025-02-05T13:16:41Z)
• AnnotatedTables: A Large Tabular Dataset with Language Model Annotations [8.602181445598776]
  We show how machine learning can be used to automate the annotation of large volumes of diverse tabular data. We release AnnotatedTables, a collection of 32,119 databases with LLM-generated annotations. We evaluate the performance of TabPFN, a recent neural classifier trained on Bayesian priors, on 2,720 tables with input-target columns identified by LLMs.
  arXiv  Detail & Related papers  (2024-06-24T06:44:14Z)
• Unleashing the Potential of Large Language Models for Predictive Tabular Tasks in Data Science [17.282770819829913]
  This research endeavors to apply Large Language Models (LLMs) towards addressing these predictive tasks.<n>Our research aims to mitigate this gap by compiling a comprehensive corpus of tables annotated with instructions and executing large-scale training of Llama-2.
  arXiv  Detail & Related papers  (2024-03-29T14:41:21Z)
• TableLLM: Enabling Tabular Data Manipulation by LLMs in Real Office Usage Scenarios [51.66718740300016]
  TableLLM is a robust large language model (LLM) with 8 billion parameters.<n>TableLLM is purpose-built for proficiently handling data manipulation tasks.<n>We have released the model checkpoint, source code, benchmarks, and a web application for user interaction.
  arXiv  Detail & Related papers  (2024-03-28T11:21:12Z)
• Making Pre-trained Language Models Great on Tabular Prediction [50.70574370855663]
  The transferability of deep neural networks (DNNs) has made significant progress in image and language processing. We present TP-BERTa, a specifically pre-trained LM for tabular data prediction. A novel relative magnitude tokenization converts scalar numerical feature values to finely discrete, high-dimensional tokens, and an intra-feature attention approach integrates feature values with the corresponding feature names.
  arXiv  Detail & Related papers  (2024-03-04T08:38:56Z)
• TabuLa: Harnessing Language Models for Tabular Data Synthesis [4.539846270369207]
  Tabula is a tabular data synthesizer that leverages the structure of large language models (LLMs)<n>Unlike state-of-the-art (SOTA) LLMs, Tabula discards the pre-trained weights originally designed for natural language tasks.<n> experiments show that Tabula achieves superior synthetic data utility compared to current SOTA methods.
  arXiv  Detail & Related papers  (2023-10-19T13:50:56Z)
• Language models are weak learners [71.33837923104808]
  We show that prompt-based large language models can operate effectively as weak learners. We incorporate these models into a boosting approach, which can leverage the knowledge within the model to outperform traditional tree-based boosting. Results illustrate the potential for prompt-based LLMs to function not just as few-shot learners themselves, but as components of larger machine learning pipelines.
  arXiv  Detail & Related papers  (2023-06-25T02:39:19Z)
• M-Tuning: Prompt Tuning with Mitigated Label Bias in Open-Set Scenarios [58.617025733655005]
  We propose a vision-language prompt tuning method with mitigated label bias (M-Tuning)<n>It introduces open words from the WordNet to extend the range of words forming the prompt texts from only closed-set label words to more, and thus prompts are tuned in a simulated open-set scenario.<n>Our method achieves the best performance on datasets with various scales, and extensive ablation studies also validate its effectiveness.
  arXiv  Detail & Related papers  (2023-03-09T09:05:47Z)
• Benchmarking Multimodal AutoML for Tabular Data with Text Fields [83.43249184357053]
  We assemble 18 multimodal data tables that each contain some text fields. Our benchmark enables researchers to evaluate their own methods for supervised learning with numeric, categorical, and text features.
  arXiv  Detail & Related papers  (2021-11-04T09:29:16Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.