# Fairness-Aware Structured Pruning in Transformers

arXiv: https://arxiv.org/abs/2312.15398 · HTML: https://mlsanity.com/paper/2312.15398/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- Builds on 35 of its 47 references that are in the map.
- First posted on arXiv 24 Dec 2023.

## Builds on (most cited first, 30 of 35)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding](https://mlsanity.com/paper/1804.07461/) (2018)
- [SQuAD: 100,000+ Questions for Machine Comprehension of Text](https://mlsanity.com/paper/1606.05250/) (2016)
- [Pointer Sentinel Mixture Models](https://mlsanity.com/paper/1609.07843/) (2016)
- [Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding](https://mlsanity.com/paper/1510.00149/) (2015)
- [The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks](https://mlsanity.com/paper/1803.03635/) (2018)
- [Learning both Weights and Connections for Efficient Neural Networks](https://mlsanity.com/paper/1506.02626/) (2015)
- [Know What You Don't Know: Unanswerable Questions for SQuAD](https://mlsanity.com/paper/1806.03822/) (2018)
- [Scaling Language Models: Methods, Analysis & Insights from Training Gopher](https://mlsanity.com/paper/2112.11446/) (2021)
- [Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small](https://mlsanity.com/paper/2211.00593/) (2022)
- [StereoSet: Measuring stereotypical bias in pretrained language models](https://mlsanity.com/paper/2004.09456/) (2020)
- [Semantics derived automatically from language corpora contain human-like biases](https://mlsanity.com/paper/1608.07187/) (2016)
- [Analyzing Multi-Head Self-Attention: Specialized Heads Do the Heavy Lifting, the Rest Can Be Pruned](https://mlsanity.com/paper/1905.09418/) (2019)
- [CrowS-Pairs: A Challenge Dataset for Measuring Social Biases in Masked Language Models](https://mlsanity.com/paper/2010.00133/) (2020)
- [Using DeepSpeed and Megatron to Train Megatron-Turing NLG 530B, A Large-Scale Generative Language Model](https://mlsanity.com/paper/2201.11990/) (2022)
- [Gender Bias in Coreference Resolution](https://mlsanity.com/paper/1804.09301/) (2018)
- [Reducing Transformer Depth on Demand with Structured Dropout](https://mlsanity.com/paper/1909.11556/) (2019)
- [BOLD: Dataset and Metrics for Measuring Biases in Open-Ended Language Generation](https://mlsanity.com/paper/2101.11718/) (2021)
- [Measuring Bias in Contextualized Word Representations](https://mlsanity.com/paper/1906.07337/) (2019)
- [Measuring and Reducing Gendered Correlations in Pre-trained Models](https://mlsanity.com/paper/2010.06032/) (2020)
- [A Unified MRC Framework for Named Entity Recognition](https://mlsanity.com/paper/1910.11476/) (2019)
- [Dice Loss for Data-imbalanced NLP Tasks](https://mlsanity.com/paper/1911.02855/) (2019)
- [Detecting Emergent Intersectional Biases: Contextualized Word Embeddings Contain a Distribution of Human-like Biases](https://mlsanity.com/paper/2006.03955/) (2020)
- ["I'm sorry to hear that": Finding New Biases in Language Models with a Holistic Descriptor Dataset](https://mlsanity.com/paper/2205.09209/) (2022)
- [Named Entity Recognition as Dependency Parsing](https://mlsanity.com/paper/2005.07150/) (2020)
- [On the Effect of Dropping Layers of Pre-trained Transformer Models](https://mlsanity.com/paper/2004.03844/) (2020)
- [When BERT Plays the Lottery, All Tickets Are Winning](https://mlsanity.com/paper/2005.00561/) (2020)
- [Exploring Sparsity in Recurrent Neural Networks](https://mlsanity.com/paper/1704.05119/) (2017)

## Built on by (most cited first, 22 of 22)

- [FairSteer: Inference Time Debiasing for LLMs with Dynamic Activation Steering](https://mlsanity.com/paper/2504.14492/) (2025)
- [GuidedQuant: Large Language Model Quantization via Exploiting End Loss Guidance](https://mlsanity.com/paper/2505.07004/) (2025)
- [Fairness and Bias in Multimodal AI: A Survey](https://mlsanity.com/paper/2406.19097/) (2024)
- [Programming with AI: Evaluating ChatGPT, Gemini, AlphaCode, and GitHub Copilot for Programmers](https://mlsanity.com/paper/2411.09224/) (2024)
- [Attention Pruning: Automated Fairness Repair of Language Models via Surrogate Simulated Annealing](https://mlsanity.com/paper/2503.15815/) (2025)
- [Evaluating and Improving Robustness in Large Language Models: A Survey and Future Directions](https://mlsanity.com/paper/2506.11111/) (2025)
- [CoBia: Constructed Conversations Can Trigger Otherwise Concealed Societal Biases in LLMs](https://mlsanity.com/paper/2510.09871/) (2025)
- [Why Don't Prompt-Based Fairness Metrics Correlate?](https://mlsanity.com/paper/2406.05918/) (2024)
- [Debiasing surgeon: fantastic weights and how to find them](https://mlsanity.com/paper/2403.14200/) (2024)
- [Breaking Down Bias: On The Limits of Generalizable Pruning Strategies](https://mlsanity.com/paper/2502.07771/) (2025)
- [Fairness in Augmented Graph Learning: A Survey](https://mlsanity.com/paper/2504.21296/) (2025)
- [Less Is More? Examining Fairness in Pruned Large Language Models for Summarising Opinions](https://mlsanity.com/paper/2508.17610/) (2025)
- [REFER: Mitigating Bias in Opinion Summarisation via Frequency Framed Prompting](https://mlsanity.com/paper/2509.15723/) (2025)
- [It Takes a MAESTRO To Prune Bad Experts](https://mlsanity.com/paper/2607.08601/) (2026)
- [DeFrame: Debiasing Large Language Models Against Framing Effects](https://mlsanity.com/paper/2602.04306/) (2026)
- [Fairness Aware Reward Optimization](https://mlsanity.com/paper/2602.07799/) (2026)
- [Auto-Search and Refinement: An Automated Framework for Gender Bias Mitigation in Large Language Models](https://mlsanity.com/paper/2502.11559/) (2025)
- [A Close Reading Approach to Gender Narrative Biases in AI-Generated Stories](https://mlsanity.com/paper/2508.09651/) (2025)
- [HiCoLoRA: Addressing Context-Prompt Misalignment via Hierarchical Collaborative LoRA for Zero-Shot DST](https://mlsanity.com/paper/2509.19742/) (2025)
- [Debiasing LLMs by Masking Unfairness-Driving Attention Heads](https://mlsanity.com/paper/2510.10142/) (2025)
- [Bias In, Bias Out? Finding Unbiased Subnetworks in Vanilla Models](https://mlsanity.com/paper/2603.05582/) (2026)
- [FORGE: Verification-Gated Behavioral Repair for Generative Language Models](https://mlsanity.com/paper/2610.05190/) (2026)

## Abstract (arXiv)

The increasing size of large language models (LLMs) has introduced challenges in their training and inference. Removing model components is perceived as a solution to tackle the large model sizes, however, existing pruning methods solely focus on performance, without considering an essential aspect for the responsible use of LLMs: model fairness. It is crucial to address the fairness of LLMs towards diverse groups, such as women, Black people, LGBTQ+, Jewish communities, among others, as they are being deployed and available to a wide audience. In this work, first, we investigate how attention heads impact fairness and performance in pre-trained transformer-based language models. We then propose a novel method to prune the attention heads that negatively impact fairness while retaining the heads critical for performance, i.e. language modeling capabilities. Our approach is practical in terms of time and resources, as it does not require fine-tuning the final pruned, and fairer, model. Our findings demonstrate a reduction in gender bias by 19%, 19.5%, 39.5%, 34.7%, 23%, and 8% for DistilGPT-2, GPT-2, GPT-Neo of two different sizes, GPT-J, and Llama 2 models, respectively, in comparison to the biased model, with only a slight decrease in performance.