# Fair In-Context Learning via Latent Concept Variables

arXiv: https://arxiv.org/abs/2411.02671 · HTML: https://mlsanity.com/paper/2411.02671/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 33 references that are in the map.
- First posted on arXiv 4 Nov 2024.

## Builds on (most cited first, 23 of 23)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Equality of Opportunity in Supervised Learning](https://mlsanity.com/paper/1610.02413/) (2016)
- [What Makes Good In-Context Examples for GPT-3?](https://mlsanity.com/paper/2101.06804/) (2021)
- [Fantastically Ordered Prompts and Where to Find Them: Overcoming Few-Shot Prompt Order Sensitivity](https://mlsanity.com/paper/2104.08786/) (2021)
- [An Explanation of In-context Learning as Implicit Bayesian Inference](https://mlsanity.com/paper/2111.02080/) (2021)
- [Learning To Retrieve Prompts for In-Context Learning](https://mlsanity.com/paper/2112.08633/) (2021)
- [Bias and Fairness in Large Language Models: A Survey](https://mlsanity.com/paper/2309.00770/) (2023)
- [DecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT Models](https://mlsanity.com/paper/2306.11698/) (2023)
- [TabLLM: Few-shot Classification of Tabular Data with Large Language Models](https://mlsanity.com/paper/2210.10723/) (2022)
- [Selective Annotation Makes Language Models Better Few-Shot Learners](https://mlsanity.com/paper/2209.01975/) (2022)
- [Large Language Models in Finance: A Survey](https://mlsanity.com/paper/2311.10723/) (2023)
- [A survey on datasets for fairness-aware machine learning](https://mlsanity.com/paper/2110.00530/) (2021)
- [Large Language Models Are Latent Variable Models: Explaining and Finding Good Demonstrations for In-Context Learning](https://mlsanity.com/paper/2301.11916/) (2023)
- [Evaluating the Underlying Gender Bias in Contextualized Word Embeddings](https://mlsanity.com/paper/1904.08783/) (2019)
- [Fairness-guided Few-shot Prompting for Large Language Models](https://mlsanity.com/paper/2303.13217/) (2023)
- [A Short Survey of Viewing Large Language Models in Legal Aspect](https://mlsanity.com/paper/2303.09136/) (2023)
- [Uncovering Implicit Gender Bias in Narratives through Commonsense Inference](https://mlsanity.com/paper/2109.06437/) (2021)
- [Fairness of ChatGPT](https://mlsanity.com/paper/2305.18569/) (2023)
- [Few-Shot Fairness: Unveiling LLM's Potential for Fairness-Aware Classification](https://mlsanity.com/paper/2402.18502/) (2024)
- [Confronting LLMs with Traditional ML: Rethinking the Fairness of Large Language Models in Tabular Classifications](https://mlsanity.com/paper/2310.14607/) (2023)
- [DP-TabICL: In-Context Learning with Differentially Private Tabular Data](https://mlsanity.com/paper/2403.05681/) (2024)
- [Strategic Demonstration Selection for Improved Fairness in LLM In-Context Learning](https://mlsanity.com/paper/2408.09757/) (2024)

## Built on by (most cited first, 3 of 3)

- [FairPFN: A Tabular Foundation Model for Causal Fairness](https://mlsanity.com/paper/2506.07049/) (2025)
- [Towards Fair In-Context Learning with Tabular Foundation Models](https://mlsanity.com/paper/2505.09503/) (2025)
- [Proxy reliance in large language model decisions is uncalibrated to predictive evidence](https://mlsanity.com/paper/2608.22887/) (2026)

## Abstract (arXiv)

The emerging in-context learning (ICL) ability of large language models (LLMs) has prompted their use for predictive tasks in various domains with different data types, including tabular data, facilitated by serialization methods. However, with increasing applications in high-stakes domains, it has been shown that LLMs can inherit social bias and discrimination from their pre-training data. In this work, we investigate inherent bias in LLMs during in-context learning with tabular data. We focus on an optimal demonstration selection approach that utilizes latent concept variables for resource-efficient task adaptation. We design data augmentation strategies that reduce the correlation between predictive outcomes and sensitive variables, helping promote fairness during latent concept learning. We utilize the learned concept to select demonstrations and obtain fair predictions. The latent concept variables are learned using a smaller internal LLM and generalized to larger external LLMs. We empirically verify that the fair latent variable approach improves fairness results on tabular datasets compared to multiple heuristic demonstration selection methods.