# Mitigating Social Biases in Language Models through Unlearning

arXiv: https://arxiv.org/abs/2406.13551 · HTML: https://mlsanity.com/paper/2406.13551/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Placed in Machine unlearning, one of 12 directions in LLM safety and security.
- Builds on 24 of its 33 references that are in the map.
- First posted on arXiv 19 Jun 2024.

## Placed in

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

## Builds on (most cited first, 24 of 24)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge](https://mlsanity.com/paper/1803.05457/) (2018)
- [HellaSwag: Can a Machine Really Finish Your Sentence?](https://mlsanity.com/paper/1905.07830/) (2019)
- [Pointer Sentinel Mixture Models](https://mlsanity.com/paper/1609.07843/) (2016)
- [PIQA: Reasoning about Physical Commonsense in Natural Language](https://mlsanity.com/paper/1911.11641/) (2019)
- [Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering](https://mlsanity.com/paper/1809.02789/) (2018)
- [Know What You Don't Know: Unanswerable Questions for SQuAD](https://mlsanity.com/paper/1806.03822/) (2018)
- [Machine Unlearning](https://mlsanity.com/paper/1912.03817/) (2019)
- [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)
- [BBQ: A Hand-Built Bias Benchmark for Question Answering](https://mlsanity.com/paper/2110.08193/) (2021)
- [Making AI Forget You: Data Deletion in Machine Learning](https://mlsanity.com/paper/1907.05012/) (2019)
- [Knowledge Unlearning for Mitigating Privacy Risks in Language Models](https://mlsanity.com/paper/2210.01504/) (2022)
- [BOLD: Dataset and Metrics for Measuring Biases in Open-Ended Language Generation](https://mlsanity.com/paper/2101.11718/) (2021)
- [Studying Large Language Model Generalization with Influence Functions](https://mlsanity.com/paper/2308.03296/) (2023)
- [Modifying Memories in Transformer Models](https://mlsanity.com/paper/2012.00363/) (2020)
- [Composing Parameter-Efficient Modules with Arithmetic Operations](https://mlsanity.com/paper/2306.14870/) (2023)
- [KGA: A General Machine Unlearning Framework Based on Knowledge Gap Alignment](https://mlsanity.com/paper/2305.06535/) (2023)
- [Fast Model Debias with Machine Unlearning](https://mlsanity.com/paper/2310.12560/) (2023)
- [SaFeRDialogues: Taking Feedback Gracefully after Conversational Safety Failures](https://mlsanity.com/paper/2110.07518/) (2021)
- [SAFE: Machine Unlearning With Shard Graphs](https://mlsanity.com/paper/2304.13169/) (2023)
- [`A-la-carte Prompt Tuning (APT): Combining Distinct Data Via Composable Prompting](https://mlsanity.com/paper/2302.07994/) (2023)
- [Fuse to Forget: Bias Reduction and Selective Memorization through Model Fusion](https://mlsanity.com/paper/2311.07682/) (2023)

## Built on by (most cited first, 7 of 7)

- [Model Merging in LLMs, MLLMs, and Beyond: Methods, Theories, Applications and Opportunities](https://mlsanity.com/paper/2408.07666/) (2024)
- [LLM Unlearning via Neural Activation Redirection](https://mlsanity.com/paper/2502.07218/) (2025)
- [Aligned but Blind: Alignment Increases Implicit Bias by Reducing Awareness of Race](https://mlsanity.com/paper/2506.00253/) (2025)
- [AesBiasBench: Evaluating Bias and Alignment in Multimodal Language Models for Personalized Image Aesthetic Assessment](https://mlsanity.com/paper/2509.11620/) (2025)
- [A Survey on Unlearning in Large Language Models](https://mlsanity.com/paper/2510.25117/) (2025)
- [From n-gram to Attention: How Model Architectures Learn and Propagate Bias in Language Modeling](https://mlsanity.com/paper/2505.12381/) (2025)
- [Soft Weighted Machine Unlearning](https://mlsanity.com/paper/2505.18783/) (2025)

## Abstract (arXiv)

Mitigating bias in language models (LMs) has become a critical problem due to the widespread deployment of LMs. Numerous approaches revolve around data pre-processing and fine-tuning of language models, tasks that can be both time-consuming and computationally demanding. Consequently, there is a growing interest in machine unlearning techniques given their capacity to induce the forgetting of undesired behaviors of the existing pre-trained or fine-tuned models with lower computational cost. In this work, we explore two unlearning methods, (1) Partitioned Contrastive Gradient Unlearning (PCGU) applied on decoder models and (2) Negation via Task Vector, to reduce social biases in state-of-the-art and open-source LMs such as LLaMA-2 and OPT. We also implement distributed PCGU for large models. It is empirically shown, through quantitative and qualitative analyses, that negation via Task Vector method outperforms PCGU in debiasing with minimum deterioration in performance and perplexity of the models. On LLaMA-27B, negation via Task Vector reduces the bias score by 11.8%