@inproceedings{Wijaya_NeurIPS25a,
TITLE = {Post Hoc Regression Refinement via Pairwise Rankings},
AUTHOR = {Wijaya, Kevin Tirta and Sun, Michael and Guo, Minghao and Seidel, Hans-Peter and Matusik, Wojciech and Babaei, Vahid},
LANGUAGE = {eng},
PUBLISHER = {Curran Associates, Inc.},
YEAR = {2025},
PUBLREMARK = {Accepted},
MARGINALMARK = {$\bullet$},
ABSTRACT = {Accurate prediction of continuous properties is essential to many scientific and engineering tasks. Although deep-learning regressors excel with abundant labels, their accuracy deteriorates in data-scarce regimes. We introduce RankRefine, a model-agnostic, plug-and-play post hoc method that refines regression with expert knowledge coming from pairwise rankings. Given a query item and a small reference set with known properties, RankRefine combines the base regressor's output with a rank-based estimate via inverse variance weighting, requiring no retraining. In molecular property prediction task, RankRefine achieves up to 10% relative reduction in mean absolute error using only 20 pairwise comparisons obtained through a general-purpose large language model (LLM) with no finetuning. As rankings provided by human experts or general-purpose LLMs are sufficient for improving regression across diverse domains, RankRefine offers practicality and broad applicability, especially in low-data settings.},
BOOKTITLE = {Advances in Neural Information Processing Systems 38},
ADDRESS = {San Diego, CA, USA},
}