# Task Expansion and Cross Refinement for Open-World Conditional Modeling

arXiv: https://arxiv.org/abs/2603.13308 · HTML: https://mlsanity.com/paper/2603.13308/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 28 references that are in the map.
- First posted on arXiv 3 Mar 2026.

## Builds on (most cited first, 18 of 18)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Emergent Abilities of Large Language Models](https://mlsanity.com/paper/2206.07682/) (2022)
- [TabPFN: A Transformer That Solves Small Tabular Classification Problems in a Second](https://mlsanity.com/paper/2207.01848/) (2022)
- [Language Models are Realistic Tabular Data Generators](https://mlsanity.com/paper/2210.06280/) (2022)
- [TabICL: A Tabular Foundation Model for In-Context Learning on Large Data](https://mlsanity.com/paper/2502.05564/) (2025)
- [Large Language Models Can Automatically Engineer Features for Few-Shot Tabular Learning](https://mlsanity.com/paper/2404.09491/) (2024)
- [Making Pre-trained Language Models Great on Tabular Prediction](https://mlsanity.com/paper/2403.01841/) (2024)
- [Curated LLM: Synergy of LLMs and Data Curation for tabular augmentation in low-data regimes](https://mlsanity.com/paper/2312.12112/) (2023)
- [STUNT: Few-shot Tabular Learning with Self-generated Tasks from Unlabeled Tables](https://mlsanity.com/paper/2303.00918/) (2023)
- [A Closer Look at TabPFN v2: Understanding Its Strengths and Extending Its Capabilities](https://mlsanity.com/paper/2502.17361/) (2025)
- [MediTab: Scaling Medical Tabular Data Predictors via Data Consolidation, Enrichment, and Refinement](https://mlsanity.com/paper/2305.12081/) (2023)
- [From Supervised to Generative: A Novel Paradigm for Tabular Deep Learning with Large Language Models](https://mlsanity.com/paper/2310.07338/) (2023)
- [Arbitrary Conditional Distributions with Energy](https://mlsanity.com/paper/2102.04426/) (2021)
- [Towards Cross-Table Masked Pretraining for Web Data Mining](https://mlsanity.com/paper/2307.04308/) (2023)
- [CTSyn: A Foundation Model for Cross Tabular Data Generation](https://mlsanity.com/paper/2406.04619/) (2024)
- [Revisiting Self-Training with Regularized Pseudo-Labeling for Tabular Data](https://mlsanity.com/paper/2302.14013/) (2023)
- [CAST: Cluster-Aware Self-Training for Tabular Data via Reliable Confidence](https://mlsanity.com/paper/2310.06380/) (2023)

## Built on by (most cited first, 1 of 1)

- [MulTaBench: Benchmarking Multimodal Tabular Learning with Text and Image](https://mlsanity.com/paper/2605.10616/) (2026)

## Abstract (arXiv)

Open-world conditional modeling (OCM), requires a single model to answer arbitrary conditional queries across heterogeneous datasets, where observed variables and targets vary and arise from a vast open-ended task universe. Because any finite collection of real-world datasets covers only a small fraction of this space, we propose Task Expansion and Cross Refinement (TEXR), a semi-supervised framework that enlarges effective task coverage through structured synthesis and refinement of semantic data contexts. TEXR first generates diverse uninstantiated dataset schemas and weakly instantiates them via structured probabilistic generators guided by large language models. It then performs cross-model refinement by training on disjoint data partitions and revising synthetic values across splits to reduce confirmation bias and improve pseudo-value quality. The refined synthetic datasets are aggregated with real data to train a unified conditional model. Across heterogeneous tabular benchmarks, TEXR consistently improves zero-, few-, and many-shot performance for multiple OCM backbones, demonstrating that structured task expansion and cross refinement enhance open-world conditional modeling.