mlsanityData to 14 Oct 2026

Post Hoc Regression Refinement via Pairwise Rankings

arXiv 2508.16495 ↗First posted 22 Aug 2025cs.LG cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 15 of its 43 references that are in the map. First posted on arXiv 22 Aug 2025.

Builds on

15 of 43 references.

References · 15

  1. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 8,065
  2. 2022Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedbackcited by 3,720
  3. 2017MoleculeNet: A Benchmark for Molecular Machine Learningcited by 1,051
  4. 2023Instruction Tuning for Large Language Models: A Surveycited by 623
  5. 2017Age Progression/Regression by Conditional Adversarial Autoencodercited by 429
  6. 2021Therapeutics Data Commons: Machine Learning Datasets and Tasks for Drug Discovery and Developmentcited by 264
  7. 2023What can Large Language Models do in chemistry? A comprehensive benchmark on eight taskscited by 185
  8. 2024MolecularGPT: Open Large Language Model (LLM) for Few-Shot Molecular Property Predictioncited by 24
  9. 2020Learning Inconsistent Preferences with Gaussian Processescited by 12
  10. 2024Regression with Large Language Models for Materials and Molecular Property Predictioncited by 11
  11. 2024Consolidating Ranking and Relevance Predictions of Large Language Models through Post-Processingcited by 9
  12. 2024Representing Molecules as Random Walks Over Interpretable Grammarscited by 7
3 more
  1. 2024RankUp: Boosting Semi-Supervised Regression with an Auxiliary Ranking Classifiercited by 6
  2. 2025Foundation Molecular Grammar: Multi-Modal Foundation Models Induce Interpretable Molecular Graph Languagescited by 6
  3. 2024Ranking over Regression for Bayesian Optimization and Molecule Selectioncited by 4

Built on by

Not cited yet.