REVIEW 16 cited by
Large Language Models(LLMs) on Tabular Data: Prediction, Generation, and Understanding -- A Survey
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Recent breakthroughs in large language modeling have facilitated rigorous exploration of their application in diverse tasks related to tabular data modeling, such as prediction, tabular data synthesis, question answering, and table understanding. Each task presents unique challenges and opportunities. However, there is currently a lack of comprehensive review that summarizes and compares the key techniques, metrics, datasets, models, and optimization approaches in this research domain. This survey aims to address this gap by consolidating recent progress in these areas, offering a thorough survey and taxonomy of the datasets, metrics, and methodologies utilized. It identifies strengths, limitations, unexplored territories, and gaps in the existing literature, while providing some insights for future research directions in this vital and rapidly evolving field. It also provides relevant code and datasets references. Through this comprehensive review, we hope to provide interested readers with pertinent references and insightful perspectives, empowering them with the necessary tools and knowledge to effectively navigate and address the prevailing challenges in the field.
Forward citations
Cited by 16 Pith papers
-
Watermarking Large Language Model-based Time Series Forecasting
Waltz embeds watermarks into LLM-based time series forecasts by nudging a few patch embeddings toward 'cold' LLM tokens, and detects them with a z-score test.
-
Orthogonal Hierarchical Decomposition for Structure-Aware Table Understanding with Large Language Models
A framework that splits tables into row-tree and column-tree representations and uses an LLM to arbitrate both achieves large gains on complex-table QA benchmarks, though one backbone underperforms on HiTab.
-
MetaRank: Task-Aware Metric Selection for Model Transferability Estimation
A meta-learner ranks MTE metrics for a target dataset from text descriptions, improving average rank over fixed metrics on 11 datasets.
-
Limited Reference, Reliable Generation: A Two-Component Framework for Tabular Data Generation in Low-Data Regimes
ReFine combines rule-guided prompting and dual-granularity filtering to improve LLM-based tabular data generation when only 30 to 90 labeled rows exist, achieving top average rank over baselines.
-
Towards Agents That Know When They Don't Know: Uncertainty as a Control Signal for Structured Reasoning
An LLM agent using retrieval and summary uncertainty as training rewards and inference filters produces more factual, useful multi-omics summaries and better downstream survival predictions.
-
AraTable: Benchmarking LLMs' Reasoning and Understanding of Arabic Tabular Data
AraTable is the first Arabic tabular QA benchmark; its experiments show LLMs are much weaker at reasoning over Arabic tables than at direct lookup.
-
Tab-MIA: A Benchmark Dataset for Membership Inference Attacks on Tabular Data in LLMs
Tab-MIA shows LLMs fine-tuned on tabular data are vulnerable to membership inference attacks, with AUROC up to 97.7% after three epochs and encoding format strongly affecting leakage.
-
Table Understanding and (Multimodal) LLMs: A Cross-Domain Case Study on Scientific vs. Non-Scientific Data
A new benchmark, TableEval, with 3017 tables in five formats, shows LLMs are robust to table representation but perform worse on scientific tables, with the caveat that the domain gap is confounded by task difficulty.
-
An LLM-Based Automatic Sportscast Solution for Robot Soccer Matches
A neuro-symbolic pipeline turns RoboCup robot-soccer video into real-time statistics and LLM-generated commentary, demonstrated on three German Open 2026 clips.
-
A Survey on Evaluating Quality and Trustworthiness in LLM-Generated Data
A metric-oriented survey that classifies intrinsic quality and trustworthiness metrics for LLM-generated data across six modalities and documents systematic evaluation gaps in the current literature.
-
Multimodal Behavioral Patterns Analysis with Eye-Tracking and LLM-Based Reasoning
A human-AI framework uses horizontal and vertical segmentation with LLMs, expert co-scoring, and LSTM anomaly detection to extract behavioral patterns from eye-tracking data.
-
Large Language Models as Unified Multimodal Learners for Clinical Prediction
Serializing all patient data — notes, vitals, labs — into one text sequence and fine-tuning an LLM matches or beats task-specific multimodal fusion baselines on mortality, graft-failure, and triage prediction.
-
A Generalised Exponentiated Gradient Approach to Enhance Fairness in Binary and Multi-class Classification Tasks
A generalized Exponentiated Gradient method trains binary and multi-class classifiers under multiple linear fairness constraints, achieving fairness gains up to 92% at an accuracy cost up to 14 points.
-
Agentic LLMs for Question Answering over Tabular Data
A five-stage NL-to-SQL pipeline with GPT-4o achieves 70.5% on DataBench QA and 71.6% on DataBench Lite QA, beating baselines of 26% and 27%.
-
Towards High Supervised Learning Utility Training Data Generation: Data Pruning and Column Reordering
PRRO combines signal-based data pruning and column reordering to improve the supervised learning utility of synthetic tabular data, but its evaluation is undermined by data manipulation and an ill-defined correlation measure.
-
Tabular Data Understanding with LLMs: A Survey of Recent Advances and Challenges
A structured review of table understanding with LLMs that proposes a taxonomy of input representations and identifies three research gaps.
Discussion (0). Sign in to comment.