Research map / Label-efficient and robust learning / Recognition and long-tail
When Tabular Foundation Models Meet Strategic Tabular Data: A Prior Alignment Approach
Xinpeng Lv, Yunxin Mao, Renzhe Xu, Chunyuan Zheng, Yikai Chen, Haoxuan Li, Jinxuan Yang, Yuanlong Chen, Kun Kuang, Mingyang Geng, Shixuan Liu, Wanrong Huang and 4 more
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| construct in-context examples from strategic (manipulated) data instead of non-strategic data | TabPFN backbone (SPN) · Adult, Spambase and other strategic benchmarks | accuracy under manipulation | Improved |
| increase number of in-context strategic examples k from 10 to about 50 (ablation) | SPN · four manipulation regimes | accuracy | Improved |
| increase number of in-context examples beyond about 50 (ablation) | SPN · four manipulation regimes | accuracy | No clear effect |
| use SPN strategic context instead of plain TabPFN on non-strategic data | TabPFN v2.5 · Bank (non-strategic) | AUC-ROC (%): 91.85 -> 91.65 | No clear effect |
| build strategic context from a single manipulation regime and test on other regimes | SPN · Noisy, heterogeneous and mixed manipulation | accuracy | Improved |
| use in-context learning instead of fine-tuning for adapting to manipulation | PFN classifier · semi-synthetic email spam | update time and data cost | Improved |
Closest papers by meaning
- Understanding the Surprising Generalization Properties of Tabular Foundation Models (NeurIPS 2026 · similarity 0.89)
- Tabular Foundation Model for Generative Modelling (NeurIPS 2026 · similarity 0.88)
- A Closer Look at TabPFN v2: Understanding Its Strengths and Extending Its Capabilities (NeurIPS 2025 · similarity 0.88)
- Strengthening LLMs for Tabular Prediction with Structural Priors (NeurIPS 2026 · similarity 0.88)
- TuneTables: Context Optimization for Scalable Prior-Data Fitted Networks (NeurIPS 2024 · similarity 0.87)
- TabDPT: Scaling Tabular Foundation Models on Real Data (NeurIPS 2025 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
