# In-Context Bias Propagation in LLM-Based Tabular Data Generation

arXiv: https://arxiv.org/abs/2506.09630 · HTML: https://mlsanity.com/paper/2506.09630/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 34 of its 42 references that are in the map.
- First posted on arXiv 11 Jun 2025.

## Builds on (most cited first, 30 of 34)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [A Survey on Bias and Fairness in Machine Learning](https://mlsanity.com/paper/1908.09635/) (2019)
- [An Explanation of In-context Learning as Implicit Bayesian Inference](https://mlsanity.com/paper/2111.02080/) (2021)
- [StereoSet: Measuring stereotypical bias in pretrained language models](https://mlsanity.com/paper/2004.09456/) (2020)
- [CrowS-Pairs: A Challenge Dataset for Measuring Social Biases in Masked Language Models](https://mlsanity.com/paper/2010.00133/) (2020)
- [Modeling Tabular data using Conditional GAN](https://mlsanity.com/paper/1907.00503/) (2019)
- [BOLD: Dataset and Metrics for Measuring Biases in Open-Ended Language Generation](https://mlsanity.com/paper/2101.11718/) (2021)
- [Larger language models do in-context learning differently](https://mlsanity.com/paper/2303.03846/) (2023)
- [TabDDPM: Modelling Tabular Data with Diffusion Models](https://mlsanity.com/paper/2209.15421/) (2022)
- [Self-Diagnosis and Self-Debiasing: A Proposal for Reducing Corpus-Based Bias in NLP](https://mlsanity.com/paper/2103.00453/) (2021)
- [Language Models are Realistic Tabular Data Generators](https://mlsanity.com/paper/2210.06280/) (2022)
- [Mixed-Type Tabular Data Synthesis with Score-based Diffusion in Latent Space](https://mlsanity.com/paper/2310.09656/) (2023)
- [CTAB-GAN: Effective Table Data Synthesizing](https://mlsanity.com/paper/2102.08369/) (2021)
- [Queens are Powerful too: Mitigating Gender Bias in Dialogue Generation](https://mlsanity.com/paper/1911.03842/) (2019)
- [BadRAG: Identifying Vulnerabilities in Retrieval Augmented Generation of Large Language Models](https://mlsanity.com/paper/2406.00083/) (2024)
- [In-Context Learning through the Bayesian Prism](https://mlsanity.com/paper/2306.04891/) (2023)
- [A Systematic Study of Bias Amplification](https://mlsanity.com/paper/2201.11706/) (2022)
- [Poisoning Attacks on Algorithmic Fairness](https://mlsanity.com/paper/2004.07401/) (2020)
- [Data Augmentation Using GANs](https://mlsanity.com/paper/1904.09135/) (2019)
- [Fairness Through Robustness: Investigating Robustness Disparity in Deep Learning](https://mlsanity.com/paper/2006.12621/) (2020)
- [Fairness-guided Few-shot Prompting for Large Language Models](https://mlsanity.com/paper/2303.13217/) (2023)
- [Curated LLM: Synergy of LLMs and Data Curation for tabular augmentation in low-data regimes](https://mlsanity.com/paper/2312.12112/) (2023)
- [Feature-Wise Bias Amplification](https://mlsanity.com/paper/1812.08999/) (2018)
- [UniBias: Unveiling and Mitigating LLM Bias through Internal Attention and FFN Manipulation](https://mlsanity.com/paper/2405.20612/) (2024)
- [Poisoning Attacks on Fair Machine Learning](https://mlsanity.com/paper/2110.08932/) (2021)
- [HARMONIC: Harnessing LLMs for Tabular Data Synthesis and Privacy Protection](https://mlsanity.com/paper/2408.02927/) (2024)
- [Confronting LLMs with Traditional ML: Rethinking the Fairness of Large Language Models in Tabular Classifications](https://mlsanity.com/paper/2310.14607/) (2023)
- [EPIC: Effective Prompting for Imbalanced-Class Data Synthesis in Tabular Data Classification via Large Language Models](https://mlsanity.com/paper/2404.12404/) (2024)
- [Strategic Demonstration Selection for Improved Fairness in LLM In-Context Learning](https://mlsanity.com/paper/2408.09757/) (2024)
- [Towards Fair In-Context Learning with Tabular Foundation Models](https://mlsanity.com/paper/2505.09503/) (2025)

## Built on by (most cited first, 1 of 1)

- [ImplicitBBQ: Benchmarking Implicit Bias in Large Language Models through Characteristic Based Cues](https://mlsanity.com/paper/2604.01925/) (2026)

## Abstract (arXiv)

Large Language Models (LLMs) are increasingly used for synthetic tabular data generation through in-context learning (ICL), offering a practical solution for data augmentation in data scarce scenarios. While prior work has shown the potential of LLMs to improve downstream task performance through augmenting underrepresented groups, these benefits often assume access to a subset of unbiased in-context examples, representative of the real dataset. In real-world settings, however, data is frequently noisy and demographically skewed. In this paper, we systematically study how statistical biases within in-context examples propagate to the distribution of synthetic tabular data, showing that even mild in-context biases lead to global statistical distortions. We further introduce an adversarial scenario where a malicious contributor can inject bias into the synthetic dataset via a subset of in-context examples, ultimately compromising the fairness of downstream classifiers for a targeted and protected subgroup. Finally, we evaluate mitigation strategies based on preprocessing in-context examples, demonstrating that while such interventions can attenuate disparity, the inherent sensitivity of LLMs to adversarial prompts remains a persistent challenge. Our findings highlight a critical new vulnerability in LLM-based data generation pipelines within sensitive domains.