# Large Language Model Bias Mitigation from the Perspective of Knowledge Editing

arXiv: https://arxiv.org/abs/2405.09341 · HTML: https://mlsanity.com/paper/2405.09341/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- Builds on 57 of its 68 references that are in the map.
- First posted on arXiv 15 May 2024.

## Builds on (most cited first, 30 of 57)

- [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)
- [Locating and Editing Factual Associations in GPT](https://mlsanity.com/paper/2202.05262/) (2022)
- [Visualizing and Understanding Convolutional Networks](https://mlsanity.com/paper/1311.2901/) (2013)
- [Language Models as Knowledge Bases?](https://mlsanity.com/paper/1909.01066/) (2019)
- [Mass-Editing Memory in a Transformer](https://mlsanity.com/paper/2210.07229/) (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)
- [A Primer in BERTology: What we know about how BERT works](https://mlsanity.com/paper/2002.12327/) (2020)
- [CrowS-Pairs: A Challenge Dataset for Measuring Social Biases in Masked Language Models](https://mlsanity.com/paper/2010.00133/) (2020)
- [Gender Bias in Coreference Resolution: Evaluation and Debiasing Methods](https://mlsanity.com/paper/1804.06876/) (2018)
- [Bias and Fairness in Large Language Models: A Survey](https://mlsanity.com/paper/2309.00770/) (2023)
- [Knowledge Neurons in Pretrained Transformers](https://mlsanity.com/paper/2104.08696/) (2021)
- [Editing Factual Knowledge in Language Models](https://mlsanity.com/paper/2104.08164/) (2021)
- [Fast Model Editing at Scale](https://mlsanity.com/paper/2110.11309/) (2021)
- [Null It Out: Guarding Protected Attributes by Iterative Nullspace Projection](https://mlsanity.com/paper/2004.07667/) (2020)
- [Memory-Based Model Editing at Scale](https://mlsanity.com/paper/2206.06520/) (2022)
- [Gender Bias in Coreference Resolution](https://mlsanity.com/paper/1804.09301/) (2018)
- [Self-Diagnosis and Self-Debiasing: A Proposal for Reducing Corpus-Based Bias in NLP](https://mlsanity.com/paper/2103.00453/) (2021)
- [Can We Edit Factual Knowledge by In-Context Learning?](https://mlsanity.com/paper/2305.12740/) (2023)
- [Aging with GRACE: Lifelong Model Editing with Discrete Key-Value Adaptors](https://mlsanity.com/paper/2211.11031/) (2022)
- [Measuring and Reducing Gendered Correlations in Pre-trained Models](https://mlsanity.com/paper/2010.06032/) (2020)
- [Gender Bias in Contextualized Word Embeddings](https://mlsanity.com/paper/1904.03310/) (2019)
- [Societal Biases in Language Generation: Progress and Challenges](https://mlsanity.com/paper/2105.04054/) (2021)
- [Counterfactual Data Augmentation for Mitigating Gender Stereotypes in Languages with Rich Morphology](https://mlsanity.com/paper/1906.04571/) (2019)
- [Transformer-Patcher: One Mistake worth One Neuron](https://mlsanity.com/paper/2301.09785/) (2023)
- [PMET: Precise Model Editing in a Transformer](https://mlsanity.com/paper/2308.08742/) (2023)
- [Towards Debiasing Sentence Representations](https://mlsanity.com/paper/2007.08100/) (2020)

## Built on by (most cited first, 16 of 16)

- [PAD: Personalized Alignment of LLMs at Decoding-Time](https://mlsanity.com/paper/2410.04070/) (2024)
- [Learnable Privacy Neurons Localization in Language Models](https://mlsanity.com/paper/2405.10989/) (2024)
- [The Mirage of Model Editing: Revisiting Evaluation in the Wild](https://mlsanity.com/paper/2502.11177/) (2025)
- [FAIntbench: A Holistic and Precise Benchmark for Bias Evaluation in Text-to-Image Models](https://mlsanity.com/paper/2405.17814/) (2024)
- [BiasAlert: A Plug-and-play Tool for Social Bias Detection in LLMs](https://mlsanity.com/paper/2407.10241/) (2024)
- [BiasEdit: Debiasing Stereotyped Language Models via Model Editing](https://mlsanity.com/paper/2503.08588/) (2025)
- [Identifying and Mitigating Social Bias Knowledge in Language Models](https://mlsanity.com/paper/2408.11843/) (2024)
- [CoME: An Unlearning-based Approach to Conflict-free Model Editing](https://mlsanity.com/paper/2502.15826/) (2025)
- [Persona-judge: Personalized Alignment of Large Language Models via Token-level Self-judgment](https://mlsanity.com/paper/2504.12663/) (2025)
- [O-Edit: Orthogonal Subspace Editing for Language Model Sequential Editing](https://mlsanity.com/paper/2410.11469/) (2024)
- [Bring Your Own Knowledge: A Survey of Methods for LLM Knowledge Expansion](https://mlsanity.com/paper/2502.12598/) (2025)
- [EvoEdit: Evolving Null-space Alignment for Robust and Efficient Knowledge Editing](https://mlsanity.com/paper/2510.13851/) (2025)
- [DiffPO: Diffusion-styled Preference Optimization for Efficient Inference-Time Alignment of Large Language Models](https://mlsanity.com/paper/2503.04240/) (2025)
- [SAKE: Towards Editing Auditory Attribute Knowledge of Large Audio-Language Models](https://mlsanity.com/paper/2510.16917/) (2025)
- [Investigating Representation Universality: Case Study on Genealogical Representations](https://mlsanity.com/paper/2410.08255/) (2024)
- [Know-MRI: A Knowledge Mechanisms Revealer&Interpreter for Large Language Models](https://mlsanity.com/paper/2506.08427/) (2025)

## Abstract (arXiv)

Existing debiasing methods inevitably make unreasonable or undesired predictions as they are designated and evaluated to achieve parity across different social groups but leave aside individual facts, resulting in modified existing knowledge. In this paper, we first establish a new bias mitigation benchmark BiasKE leveraging existing and additional constructed datasets, which systematically assesses debiasing performance by complementary metrics on fairness, specificity, and generalization. Meanwhile, we propose a novel debiasing method, Fairness Stamp (FAST), which enables editable fairness through fine-grained calibration on individual biased knowledge. Comprehensive experiments demonstrate that FAST surpasses state-of-the-art baselines with remarkable debiasing performance while not hampering overall model capability for knowledge preservation, highlighting the prospect of fine-grained debiasing strategies for editable fairness in LLMs.