Task Expansion and Cross Refinement for Open-World Conditional Modeling

TL;DR

This paper introduces TEXR, a semi-supervised framework that expands and refines datasets to improve open-world conditional modeling across diverse tasks and datasets.

Contribution

TEXR is a novel semi-supervised approach that synthesizes and refines data to enhance the coverage and performance of open-world conditional models.

Findings

TEXR improves zero-shot, few-shot, and many-shot performance across benchmarks.

Structured data synthesis and cross refinement reduce bias and enhance model accuracy.

The framework effectively enlarges task coverage in open-world settings.

Abstract

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.