Tabular Prediction

Follow this topic Ask about this topic

Tabular prediction studies how to learn from rows of examples and columns of mixed numerical, categorical, and sometimes text or relational features. Common approaches include gradient-boosted trees, feature engineering, neural networks, and tabular foundation models pretrained on synthetic data for in-context learning; graph methods can add relationships across rows or tables. Benchmarks compare these methods on classification and regression, while applied work also examines calibration, fairness, interpretability, and deployment costs. No model family dominates across settings: foundation models are often strong on small or in-distribution datasets, while large, high-dimensional, or shifted data still challenge them, making generalization and fair evaluation central open issues.

Latest papers

112 papers12 papers in the last four weeks, down 29% on the four weeks before. 0.1% of all new papers.

LLM knowledge for improved Out-of-Distribution Tabular Prediction - A Cross-Validated Regularisation Approach
Oct 27, 2026Sølve Langseth, Kristoffer Herland Hellton, Hugo L. HammerOOD Generalization Tabular Prediction
Department of Computer Science, Oslo Metropolitan University, Oslo, Norway · Department of Holistic Systems, SimulaMet, Oslo, Norway · Department of Plastic and Reconstructive Surgery, Oslo University Hospital, Oslo, Norway
Recovering Business Rules as Cascade Lookups for Enterprise Field Prediction
Oct 25, 2026Changxu DuanTabular Prediction Enterprise Analytics
Technische Universität Darmstadt, Darmstadt, Germany
Graph-to-Table Interfaces Control Relational Generalisation
Oct 19, 2026Alessandro Cagiano, Lorenzo Molfetta, Gianluca Moro +2Relational Deep Learning Tabular Prediction
University of Milan · University of Bologna · University of Edinburgh
Predicting Live Birth After Fresh Embryo Transfer in IVF/ICSI: Differential ICM/Trophectoderm Morphology Encoding and a Hybrid Attention--Logistic Regression Ensemble
Oct 15, 2026Abdul Raheem Shahzad, Jinxin Chen, Ming Zhang +1Clinical Outcome Prediction Tabular Prediction
School of Computer Science, Wuhan University, Wuhan, China · Department of Obstetrics and Gynecology, Zhongnan Hospital of Wuhan University, Wuhan, China · Reproductive Medical Center, Zhongnan Hospital of Wuhan University, Wuhan, Hubei, P.R. China, and also with the Clinical Medicine Research Center of Prenatal Diagnosis and Birth Health in Hubei Province, Wuhan, Hubei, P.R. China
OrionMoE-v1.0: A Mixture-of-Experts Foundation Model for Tabular In-Context Learning
Oct 14, 2026Mohamed Bouadi, Nassim Bouarour, Aditya Tanna +1Tabular Foundation Models Tabular ICL
Lexsi Labs
Typed Decision Models on Tabular Data
Oct 14, 2026Baowen Zhang, Hangting Ye, Hongyuan ZhaTabular Prediction Tabular ML
University of Wisconsin–Madison · School of Artificial Intelligence, Jilin University · School of Data Science, Chinese University of Hong Kong, Shenzhen
When Repeated Measurements Hurt Tabular Foundation Models
Oct 12, 2026Yixiang Liu, Ruizhe Deng, Bibhas Chakraborty +2Tabular Foundation Models Tabular Prediction
National University of Singapore · Duke-NUS Medical School · Mohamed bin Zayed University of Artificial Intelligence
MotherTree: Meta-learning on synthetic data improves decision tree training
Oct 7, 2026Ziyuan Wang, Fredrik D. JohanssonDecision Tree Learning Meta-Learning
Chalmers University of Technology University of Gothenburg
PaMIR: Open Benchmark of Public Credit-Default Datasets
Oct 2, 2026Mikhail Liashkov, Ilyas Varshavskiy, Shuhratjon Khalilbekov +2Credit Scoring Tabular Prediction
Marginal Response Surface Elicitation for Zero-Label Tabular Learning
Sep 30, 2026Liangyu Teng, Yicheng Ding, Jing Liu +5Tabular Prediction Tabular ML
Fudan Institute on Networking Systems of AI
TabFM-Auto: Self-Evolving Pipelines for Tabular Foundation Models
Sep 29, 2026Deqing Fu, Huangyuan Su, Rajat Sen +4Tabular Prediction Automated Machine Learning
Google Research · University of Southern California · Google DeepMind +2
TabFM: A Zero-Shot Foundation Model for Tabular Data
Sep 29, 2026Weihao Kong, Erez Louidor Ilan, Shuxin Nie +6Tabular Foundation Models Tabular Prediction
Google Research
Beyond Correctness: Evaluating Semantic Knowledge in Cross-Table Transfer
Sep 28, 2026Seokyong Sheem, Hochang Lee, Suyeong Lee +1Tabular ML Tabular Prediction
Korea University
What Do Tabular Foundation Models Compute In Context? In-Situ Representation Refinement through Attention-Gated Updates
Sep 23, 2026Tian Zhou, Beverly Jin, Linxiao Yang +6Tabular Foundation Models In-Context Learning
Ant Group · Independent Researcher
A JEPA Recipe for Tabular Foundation Models
Sep 22, 2026Mingyu Jeon, Suwan Cho, Jae Young SuhTabular Foundation Models Self-Supervised Pre-Training
Modulabs, Seoul, Republic of Korea
LWCal: Loss-Weighted Calibration for Tabular Classifiers with Noisy Calibration Labels
Sep 22, 2026Zeming Liu, Hang Lyu, Jingtao Zhang +1Post-Hoc Calibration Probability Calibration
Brown University · Georgia Institute of Technology · Independent Researcher
Causilo Technical Report
Sep 19, 2026Minyong Cho, Minho Jeong, Dooho Lee +2Tabular Foundation Models Tabular Prediction
LLMs as Feature Engineers for Text-and-Tabular Prediction
Sep 18, 2026Merwan Barlier, Blaz SkrljAutomated Feature Engineering Large Language Model-Based Feature Engineering
Teads
TabPFN-3.5: Technical Report
Sep 15, 2026Benjamin Jäger, Nick Erickson, Léo Grinsztajn +44Tabular Foundation Models Inference-Time Optimization
QueryFormer: Winning Solution for KDD Cup 2026 Tencent UniRec Challenge
Sep 15, 2026Yuanzhe Zhou, Zhaoyang ZengConversion Rate Prediction User Modeling
Wuhan University · Sun Yat-sen University
Agentic Search Spaces for Tabular Machine Learning
Sep 14, 2026Renat Sergazinov, Artem Chistyakov, Sergey Pankevich +1Large Language Model-Guided Optimization Tabular ML
† Yandex ‡ HSE University
A Differentially Private Federated Proximal Optimization Framework for Customer Churn Prediction in Heterogeneous Federated Telecom Networks
Sep 11, 2026Joydeb Kumar Sana, Subrata Chakraborty, M M Manjurul IslamDifferentially Private Federated Learning Tabular Prediction
Institute of Information and Communication Technology, Bangladesh University of Engineering and Technology, Dhaka, Bangladesh · School of Science and Technology, Faculty of Science, Agriculture, Business and Law, University of New England, Armidale, NSW, Australia · Intelligent Systems Research Centre, Ulster University, Londonderry BT48 7JL, UK
Quantum Feature Engineering for Credit Default Prediction: When and Why IQP Circuits Help Linear Classifiers
Sep 9, 2026Menachem Finkelstein, Diana Legziel Levy, Zohar Yakhini +1Quantum Feature Maps Quantum Machine Learning
Reichman University, Israel
The Hidden Costs of 99% Accuracy: A Trustworthiness Audit of the Telco Customer Churn Benchmark
Sep 9, 2026Soumyadeep RoyBenchmark Auditing Benchmark Contamination
Department of Data Science, St. Xavier’s College (Autonomous), Kolkata, 700016, India.
TabBench-Bio: A Living Benchmark for Machine Learning on High-Dimensional Biomedical Tables
Sep 7, 2026Jules Kreuer, Sofiane Ouaari, Julia Hellmig +2Tabular Foundation Models Tabular ML
Methods in Medical Informatics, University of Tübingen, Tübingen, Germany
Can Large Language Models Anticipate Behavioral Responses to Social Policies? A Case of Pension Enrollment Prediction among China's Flexible Workers
Sep 4, 2026Yumiao Li, Peixin Liu, Donglin Di +2LLM Evaluation Policy Evaluation
School of Economics and Management, Tsinghua University, Beijing, China · Actuarial Science and Risk Management, University of Illinois Urbana-Champaign, Urbana, IL, USA · School of Computing, Harbin Institute of Technology, Harbin, China
Mitra-v2 Technical Report
Sep 3, 2026Yefan Tao, Xiyuan Zhang, Xinyi Liu +13Tabular Foundation Models Tabular Prediction
Bernie · Amazon
Solving In-Table Prediction Problems by Deep Neural Networks with Performance Evaluation Using Synthetic Data
Sep 1, 2026Xiao Zhao, Daniela OelkeLearning with Missing Data Tabular ML
Institute for Machine Learning and Analytics Offenburg University · Department of Electrical Engineering, Medical Engineering and Computer Science Offenburg University
Births are difficult to predict even with rich survey and full-population register data
Sep 1, 2026Elizaveta Sivak, Emily M. Cantrell, Thomas Emery +109Event Time Prediction Tabular Prediction
Predicting Residential Rents in Dakar Using Machine Learning
Aug 31, 2026Amadou Tidiane Kassa DialloTabular Prediction
Dakar, Senegal

Oct 27, 2026J/K move · Enter open · S save

LLM knowledge for improved Out-of-Distribution Tabular Prediction - A Cross-Validated Regularisation Approach

Sølve Langseth, Kristoffer Herland Hellton, Hugo L. Hammer

Department of Computer Science, Oslo Metropolitan University, Oslo, Norway · Department of Holistic Systems, SimulaMet, Oslo, Norway · Department of Plastic and Reconstructive Surgery, Oslo University Hospital, Oslo, Norway

OOD Generalization Tabular Prediction Linear Regression

Open paper AskPDF arXiv

Prediction models degrade when the deployment population differs from the one used to train them, and training data cannot say which feature-response relationships will transfer. Expert elicitation is slow and unscalable. We ask whether coefficient priors elicited from large language models (LLMs) improve out-of-distribution (OOD) prediction as the shrinkage target of a regularised regression instead of zero, across five tabular datasets split on real covariates, selecting providers and prior structures by source-domain cross-validation alone. The priors help on four of five datasets, by up to 7.9% OOD mean squared error, and ten of twenty-four prior-informed results resolve the mean improvement at conventional confidence; single-deployment intervals are much wider. On classification the gain is in probabilistic accuracy, not ranking, and control tests with corrupted priors attribute the benefit to feature-specific content rather than scale. Two findings temper this. Variation across candidate priors exceeds the average benefit, yet cross-validation margins fall below their own noise, so selection avoids the worst prior rather than finding the best. On three datasets the prior improves in-domain accuracy as much as out-of-domain, making it better regularisation than shift correction. Only where the training data are large enough that the in-domain gain disappears does elicited knowledge demonstrably improve transfer. Code, priors and results: https://github.com/hugohammer/llm-priors-ood.