Task Expansion and Cross Refinement for Open-World Conditional Modeling

Shreyas Bhat Brahmavar, Qiyang Liu, Yang Li, Junier Oliva
Proceedings of the 42nd Conference on Uncertainty in Artificial Intelligence, PMLR 337:765-784, 2026.

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.

Cite this Paper

BibTeX
@InProceedings{pmlr-v337-brahmavar26a, title = {Task Expansion and Cross Refinement for Open-World Conditional Modeling}, author = {Brahmavar, Shreyas Bhat and Liu, Qiyang and Li, Yang and Oliva, Junier}, booktitle = {Proceedings of the 42nd Conference on Uncertainty in Artificial Intelligence}, pages = {765--784}, year = {2026}, editor = {Perković, Emilija and Malinsky, Daniel}, volume = {337}, series = {Proceedings of Machine Learning Research}, month = {17--21 Aug}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v337/main/assets/brahmavar26a/brahmavar26a.pdf}, url = {https://proceedings.mlr.press/v337/brahmavar26a.html}, 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.} }
Endnote
%0 Conference Paper %T Task Expansion and Cross Refinement for Open-World Conditional Modeling %A Shreyas Bhat Brahmavar %A Qiyang Liu %A Yang Li %A Junier Oliva %B Proceedings of the 42nd Conference on Uncertainty in Artificial Intelligence %C Proceedings of Machine Learning Research %D 2026 %E Emilija Perković %E Daniel Malinsky %F pmlr-v337-brahmavar26a %I PMLR %P 765--784 %U https://proceedings.mlr.press/v337/brahmavar26a.html %V 337 %X 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.
APA
Brahmavar, S.B., Liu, Q., Li, Y. & Oliva, J.. (2026). Task Expansion and Cross Refinement for Open-World Conditional Modeling. Proceedings of the 42nd Conference on Uncertainty in Artificial Intelligence, in Proceedings of Machine Learning Research 337:765-784 Available from https://proceedings.mlr.press/v337/brahmavar26a.html.

Related Material