# JoLT: Joint Probabilistic Predictions on Tabular Data Using LLMs

arXiv: https://arxiv.org/abs/2502.11877 · HTML: https://mlsanity.com/paper/2502.11877/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 34 references that are in the map.
- First posted on arXiv 17 Feb 2025.

## Builds on (most cited first, 16 of 16)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [XGBoost: A Scalable Tree Boosting System](https://mlsanity.com/paper/1603.02754/) (2016)
- [How transferable are features in deep neural networks?](https://mlsanity.com/paper/1411.1792/) (2014)
- [Deep Neural Networks and Tabular Data: A Survey](https://mlsanity.com/paper/2110.01889/) (2021)
- [TabLLM: Few-shot Classification of Tabular Data with Large Language Models](https://mlsanity.com/paper/2210.10723/) (2022)
- [Many-Shot In-Context Learning](https://mlsanity.com/paper/2404.11018/) (2024)
- [Large Language Models(LLMs) on Tabular Data: Prediction, Generation, and Understanding -- A Survey](https://mlsanity.com/paper/2402.17944/) (2024)
- [Collecting Telemetry Data Privately](https://mlsanity.com/paper/1712.01524/) (2017)
- [CARTE: Pretraining and Transfer for Tabular Learning](https://mlsanity.com/paper/2402.16785/) (2024)
- [Large Language Model for Table Processing: A Survey](https://mlsanity.com/paper/2402.05121/) (2024)
- [ORBIT: A Real-World Few-Shot Dataset for Teachable Object Recognition](https://mlsanity.com/paper/2104.03841/) (2021)
- [Heterogeneous Multi-output Gaussian Process Prediction](https://mlsanity.com/paper/1805.07633/) (2018)
- [Data Imputation using Large Language Model to Accelerate Recommendation System](https://mlsanity.com/paper/2407.10078/) (2024)
- [Endgame Analysis of Dou Shou Qi](https://mlsanity.com/paper/1604.07312/) (2016)
- [Matrix Completion with Quantified Uncertainty through Low Rank Gaussian Copula](https://mlsanity.com/paper/2006.10829/) (2020)
- [Gaussian Processes for Missing Value Imputation](https://mlsanity.com/paper/2204.04648/) (2022)

## Built on by (most cited first, 4 of 4)

- [Beyond IID: How General Are Tabular Foundation Models, Really?](https://mlsanity.com/paper/2606.30410/) (2026)
- [Eliciting Numerical Predictive Distributions of LLMs Without Autoregression](https://mlsanity.com/paper/2603.02913/) (2026)
- [MARVIS: Modality Adaptive Reasoning over VISualizations](https://mlsanity.com/paper/2507.01544/) (2025)
- [What Language Models Know But Don't Say: Non-Generative Prior Extraction for Generalization](https://mlsanity.com/paper/2601.17609/) (2026)

## Abstract (arXiv)

We introduce a simple method for probabilistic predictions on tabular data based on Large Language Models (LLMs) called JoLT (Joint LLM Process for Tabular data). JoLT uses the in-context learning capabilities of LLMs to define joint distributions over tabular data conditioned on user-specified side information about the problem, exploiting the vast repository of latent problem-relevant knowledge encoded in LLMs. JoLT defines joint distributions for multiple target variables with potentially heterogeneous data types without any data conversion, data preprocessing, special handling of missing data, or model training, making it accessible and efficient for practitioners. Our experiments show that JoLT outperforms competitive methods on low-shot single-target and multi-target tabular classification and regression tasks. Furthermore, we show that JoLT can automatically handle missing data and perform data imputation by leveraging textual side information. We argue that due to its simplicity and generality, JoLT is an effective approach for a wide variety of real prediction problems.