# Towards Fair In-Context Learning with Tabular Foundation Models

arXiv: https://arxiv.org/abs/2505.09503 · HTML: https://mlsanity.com/paper/2505.09503/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 50 references that are in the map.
- First posted on arXiv 14 May 2025.

## Builds on (most cited first, 29 of 29)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Equality of Opportunity in Supervised Learning](https://mlsanity.com/paper/1610.02413/) (2016)
- [A Survey on Bias and Fairness in Machine Learning](https://mlsanity.com/paper/1908.09635/) (2019)
- [Counterfactual Fairness](https://mlsanity.com/paper/1703.06856/) (2017)
- [Certifying and removing disparate impact](https://mlsanity.com/paper/1412.3756/) (2014)
- [TabPFN: A Transformer That Solves Small Tabular Classification Problems in a Second](https://mlsanity.com/paper/2207.01848/) (2022)
- [Mitigating Unwanted Biases with Adversarial Learning](https://mlsanity.com/paper/1801.07593/) (2018)
- [A Reductions Approach to Fair Classification](https://mlsanity.com/paper/1803.02453/) (2018)
- [Retiring Adult: New Datasets for Fair Machine Learning](https://mlsanity.com/paper/2108.04884/) (2021)
- [Learning Adversarially Fair and Transferable Representations](https://mlsanity.com/paper/1802.06309/) (2018)
- [TabICL: A Tabular Foundation Model for In-Context Learning on Large Data](https://mlsanity.com/paper/2502.05564/) (2025)
- [TabLLM: Few-shot Classification of Tabular Data with Large Language Models](https://mlsanity.com/paper/2210.10723/) (2022)
- [Flexibly Fair Representation Learning by Disentanglement](https://mlsanity.com/paper/1906.02589/) (2019)
- [A survey on datasets for fairness-aware machine learning](https://mlsanity.com/paper/2110.00530/) (2021)
- [FairBatch: Batch Selection for Model Fairness](https://mlsanity.com/paper/2012.01696/) (2020)
- [Benchmarking Distribution Shift in Tabular Data with TableShift](https://mlsanity.com/paper/2312.07577/) (2023)
- [Post-processing for Individual Fairness](https://mlsanity.com/paper/2110.13796/) (2021)
- [Active Instruction Tuning: Improving Cross-Task Generalization by Training on Prompt Sensitive Tasks](https://mlsanity.com/paper/2311.00288/) (2023)
- [Fairness-guided Few-shot Prompting for Large Language Models](https://mlsanity.com/paper/2303.13217/) (2023)
- [Fair Normalizing Flows](https://mlsanity.com/paper/2106.05937/) (2021)
- [Which Examples to Annotate for In-Context Learning? Towards Effective and Efficient Selection](https://mlsanity.com/paper/2310.20046/) (2023)
- [MAPIE: an open-source library for distribution-free uncertainty quantification](https://mlsanity.com/paper/2207.12274/) (2022)
- [Strategic Demonstration Selection for Improved Fairness in LLM In-Context Learning](https://mlsanity.com/paper/2408.09757/) (2024)
- [FairPFN: Transformers Can do Counterfactual Fairness](https://mlsanity.com/paper/2407.05732/) (2024)
- [Fairness Under Demographic Scarce Regime](https://mlsanity.com/paper/2307.13081/) (2023)
- [Survey on AI Ethics: A Socio-technical Perspective](https://mlsanity.com/paper/2311.17228/) (2023)
- [Fair In-Context Learning via Latent Concept Variables](https://mlsanity.com/paper/2411.02671/) (2024)
- [Adversarial training approach for local data debiasing](https://mlsanity.com/paper/1906.07858/) (2019)

## Built on by (most cited first, 8 of 8)

- [Uncertainty-Guided Model Selection for Tabular Foundation Models in Biomolecule Efficacy Prediction](https://mlsanity.com/paper/2510.02476/) (2025)
- [In-Context Bias Propagation in LLM-Based Tabular Data Generation](https://mlsanity.com/paper/2506.09630/) (2025)
- [A pipeline for enabling path-specific causal fairness in observational health data](https://mlsanity.com/paper/2601.09841/) (2026)
- [Causal Pre-training Under the Fairness Lens: An Empirical Study of TabPFN](https://mlsanity.com/paper/2601.17912/) (2026)
- [Training Fair Tabular Foundation Models](https://mlsanity.com/paper/2608.14211/) (2026)
- [TrustDABench: Benchmarking Reliability and Robustness of LLMs for Structured Data Analysis](https://mlsanity.com/paper/2608.24145/) (2026)
- [Conformal Prediction and Conditional Coverage for Tabular Foundation Models](https://mlsanity.com/paper/2609.34887/) (2026)
- [Parameter-Efficient Distributionally Robust Adaptation of Tabular Foundation Models under Subpopulation Shift](https://mlsanity.com/paper/2610.01143/) (2026)

## Abstract (arXiv)

Transformer-based tabular foundation models have recently demonstrated promising in-context learning (ICL) performance on structured data, emerging as competitive alternatives to gradient-boosted trees. However, the fairness implications of this new paradigm remain largely unexplored. We present the first investigation of fairness in tabular ICL, evaluating three recently proposed foundation models--TabPFNv2, TabICL, and TabDPT--on multiple benchmark datasets. To mitigate biases, we explore three pre-processing fairness-enhancing methods: correlation removal (decorrelating input features from the sensitive attribute), group-balanced sample selection (ensuring equal representation of protected groups in context examples), and uncertainty-based sample selection (prioritizing context examples with high sensitive-attribute prediction uncertainty). Our experiments show that the uncertainty-based strategy consistently improves group fairness metrics (e.g., demographic parity, equalized odds, and equal opportunity) with minimal impact on predictive accuracy. We release our code to facilitate reproducibility https://github.com/patrikken/Fair-TabICL.