# FairSISA: Ensemble Post-Processing to Improve Fairness of Unlearning in LLMs

arXiv: https://arxiv.org/abs/2312.07420 · HTML: https://mlsanity.com/paper/2312.07420/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Placed in Machine unlearning, one of 12 directions in LLM safety and security.
- Builds on 31 of its 45 references that are in the map.
- First posted on arXiv 12 Dec 2023.

## Placed in

- LLM safety and security / [Machine unlearning](https://mlsanity.com/safety/machine-unlearning/)

## Builds on (most cited first, 30 of 31)

- [Extracting Training Data from Large Language Models](https://mlsanity.com/paper/2012.07805/) (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)
- [Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings](https://mlsanity.com/paper/1607.06520/) (2016)
- [Machine Unlearning](https://mlsanity.com/paper/1912.03817/) (2019)
- [Quantifying Memorization Across Neural Language Models](https://mlsanity.com/paper/2202.07646/) (2022)
- [Mitigating Unwanted Biases with Adversarial Learning](https://mlsanity.com/paper/1801.07593/) (2018)
- [Eternal Sunshine of the Spotless Net: Selective Forgetting in Deep Networks](https://mlsanity.com/paper/1911.04933/) (2019)
- [Certified Data Removal from Machine Learning Models](https://mlsanity.com/paper/1911.03030/) (2019)
- [Making AI Forget You: Data Deletion in Machine Learning](https://mlsanity.com/paper/1907.05012/) (2019)
- [HateXplain: A Benchmark Dataset for Explainable Hate Speech Detection](https://mlsanity.com/paper/2012.10289/) (2020)
- [On Fairness and Calibration](https://mlsanity.com/paper/1709.02012/) (2017)
- [Nuanced Metrics for Measuring Unintended Bias with Real Data for Text Classification](https://mlsanity.com/paper/1903.04561/) (2019)
- [Algorithmic decision making and the cost of fairness](https://mlsanity.com/paper/1701.08230/) (2017)
- [Remember What You Want to Forget: Algorithms for Machine Unlearning](https://mlsanity.com/paper/2103.03279/) (2021)
- [Amnesiac Machine Learning](https://mlsanity.com/paper/2010.10981/) (2020)
- [A Survey of Machine Unlearning](https://mlsanity.com/paper/2209.02299/) (2022)
- [Unrolling SGD: Understanding Factors Influencing Machine Unlearning](https://mlsanity.com/paper/2109.13398/) (2021)
- [Approximate Data Deletion from Machine Learning Models](https://mlsanity.com/paper/2002.10077/) (2020)
- [Machine Unlearning of Features and Labels](https://mlsanity.com/paper/2108.11577/) (2021)
- [Machine Learning Testing: Survey, Landscapes and Horizons](https://mlsanity.com/paper/1906.10742/) (2019)
- [Social Biases in NLP Models as Barriers for Persons with Disabilities](https://mlsanity.com/paper/2005.00813/) (2020)
- [Forgetting Outside the Box: Scrubbing Deep Networks of Information Accessible from Input-Output Observations](https://mlsanity.com/paper/2003.02960/) (2020)
- [The Frontiers of Fairness in Machine Learning](https://mlsanity.com/paper/1810.08810/) (2018)
- [Does BERT Pretrained on Clinical Notes Reveal Sensitive Data?](https://mlsanity.com/paper/2104.07762/) (2021)
- [Quantifying Social Biases in NLP: A Generalization and Empirical Comparison of Extrinsic Fairness Metrics](https://mlsanity.com/paper/2106.14574/) (2021)
- [Stereotype and Skew: Quantifying Gender Bias in Pre-trained and Fine-tuned Language Models](https://mlsanity.com/paper/2101.09688/) (2021)
- [Do the Machine Learning Models on a Crowd Sourced Platform Exhibit Bias? An Empirical Study on Model Fairness](https://mlsanity.com/paper/2005.12379/) (2020)
- [Your fairness may vary: Pretrained language model fairness in toxic text classification](https://mlsanity.com/paper/2108.01250/) (2021)
- [Fair Machine Unlearning: Data Removal while Mitigating Disparities](https://mlsanity.com/paper/2307.14754/) (2023)

## Built on by (most cited first, 10 of 10)

- [Rethinking Machine Unlearning for Large Language Models](https://mlsanity.com/paper/2402.08787/) (2024)
- [Machine Unlearning in Generative AI: A Survey](https://mlsanity.com/paper/2407.20516/) (2024)
- [Digital Forgetting in Large Language Models: A Survey of Unlearning Methods](https://mlsanity.com/paper/2404.02062/) (2024)
- [Threats, Attacks, and Defenses in Machine Unlearning: A Survey](https://mlsanity.com/paper/2403.13682/) (2024)
- [Unified Parameter-Efficient Unlearning for LLMs](https://mlsanity.com/paper/2412.00383/) (2024)
- [A Survey on Unlearning in Large Language Models](https://mlsanity.com/paper/2510.25117/) (2025)
- [Debiasing Machine Unlearning with Counterfactual Examples](https://mlsanity.com/paper/2404.15760/) (2024)
- [Exploring Fairness in Educational Data Mining in the Context of the Right to be Forgotten](https://mlsanity.com/paper/2405.16798/) (2024)
- [Automating Evaluation of Diffusion Model Unlearning with (Vision-) Language Model World Knowledge](https://mlsanity.com/paper/2507.07137/) (2025)
- [UnPII: Unlearning Personally Identifiable Information with Quantifiable Exposure Risk](https://mlsanity.com/paper/2601.01786/) (2026)

## Abstract (arXiv)

Training large language models (LLMs) is a costly endeavour in terms of time and computational resources. The large amount of training data used during the unsupervised pre-training phase makes it difficult to verify all data and, unfortunately, undesirable data may be ingested during training. Re-training from scratch is impractical and has led to the creation of the 'unlearning' discipline where models are modified to "unlearn" undesirable information without retraining. However, any modification can alter the behaviour of LLMs, especially on key dimensions such as fairness. This is the first work that examines this interplay between unlearning and fairness for LLMs. In particular, we focus on a popular unlearning framework known as SISA [Bourtoule et al., 2021], which creates an ensemble of models trained on disjoint shards. We evaluate the performance-fairness trade-off for SISA, and empirically demsontrate that SISA can indeed reduce fairness in LLMs. To remedy this, we propose post-processing bias mitigation techniques for ensemble models produced by SISA. We adapt the post-processing fairness improvement technique from [Hardt et al., 2016] to design three methods that can handle model ensembles, and prove that one of the methods is an optimal fair predictor for ensemble of models. Through experimental results, we demonstrate the efficacy of our post-processing framework called 'FairSISA'.