# Potential and Challenges of Model Editing for Social Debiasing

arXiv: https://arxiv.org/abs/2402.13462 · HTML: https://mlsanity.com/paper/2402.13462/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 37 of its 55 references that are in the map.
- First posted on arXiv 21 Feb 2024.

## Builds on (most cited first, 30 of 37)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [TruthfulQA: Measuring How Models Mimic Human Falsehoods](https://mlsanity.com/paper/2109.07958/) (2021)
- [Locating and Editing Factual Associations in GPT](https://mlsanity.com/paper/2202.05262/) (2022)
- [Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering](https://mlsanity.com/paper/1809.02789/) (2018)
- [PaLM-E: An Embodied Multimodal Language Model](https://mlsanity.com/paper/2303.03378/) (2023)
- [Representation Engineering: A Top-Down Approach to AI Transparency](https://mlsanity.com/paper/2310.01405/) (2023)
- [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)
- [Stanza: A Python Natural Language Processing Toolkit for Many Human Languages](https://mlsanity.com/paper/2003.07082/) (2020)
- [CrowS-Pairs: A Challenge Dataset for Measuring Social Biases in Masked Language Models](https://mlsanity.com/paper/2010.00133/) (2020)
- [Bias and Fairness in Large Language Models: A Survey](https://mlsanity.com/paper/2309.00770/) (2023)
- [Editing Factual Knowledge in Language Models](https://mlsanity.com/paper/2104.08164/) (2021)
- [Memory-Based Model Editing at Scale](https://mlsanity.com/paper/2206.06520/) (2022)
- [Persistent Anti-Muslim Bias in Large Language Models](https://mlsanity.com/paper/2101.05783/) (2021)
- [Can We Edit Factual Knowledge by In-Context Learning?](https://mlsanity.com/paper/2305.12740/) (2023)
- [Measuring and Reducing Gendered Correlations in Pre-trained Models](https://mlsanity.com/paper/2010.06032/) (2020)
- [Modifying Memories in Transformer Models](https://mlsanity.com/paper/2012.00363/) (2020)
- [Counterfactual Data Augmentation for Mitigating Gender Stereotypes in Languages with Rich Morphology](https://mlsanity.com/paper/1906.04571/) (2019)
- [Queens are Powerful too: Mitigating Gender Bias in Dialogue Generation](https://mlsanity.com/paper/1911.03842/) (2019)
- [Reducing Sentiment Bias in Language Models via Counterfactual Evaluation](https://mlsanity.com/paper/1911.03064/) (2019)
- [Increasing Diversity While Maintaining Accuracy: Text Data Generation with Large Language Models and Human Interventions](https://mlsanity.com/paper/2306.04140/) (2023)
- [Does Gender Matter? Towards Fairness in Dialogue Systems](https://mlsanity.com/paper/1910.10486/) (2019)
- [Unmasking Contextual Stereotypes: Measuring and Mitigating BERT's Gender Bias](https://mlsanity.com/paper/2010.14534/) (2020)
- [Critic-Guided Decoding for Controlled Text Generation](https://mlsanity.com/paper/2212.10938/) (2022)
- [Using In-Context Learning to Improve Dialogue Safety](https://mlsanity.com/paper/2302.00871/) (2023)
- [Detoxifying Text with MaRCo: Controllable Revision with Experts and Anti-Experts](https://mlsanity.com/paper/2212.10543/) (2022)
- [Improving Gender Fairness of Pre-Trained Language Models without Catastrophic Forgetting](https://mlsanity.com/paper/2110.05367/) (2021)
- [Balancing out Bias: Achieving Fairness Through Balanced Training](https://mlsanity.com/paper/2109.08253/) (2021)
- [A Trip Towards Fairness: Bias and De-Biasing in Large Language Models](https://mlsanity.com/paper/2305.13862/) (2023)

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

- [Detoxifying Large Language Models via Knowledge Editing](https://mlsanity.com/paper/2403.14472/) (2024)
- [Knowledge Mechanisms in Large Language Models: A Survey and Perspective](https://mlsanity.com/paper/2407.15017/) (2024)
- [Can Knowledge Editing Really Correct Hallucinations?](https://mlsanity.com/paper/2410.16251/) (2024)
- [Can Editing LLMs Inject Harm?](https://mlsanity.com/paper/2407.20224/) (2024)
- [BiasEdit: Debiasing Stereotyped Language Models via Model Editing](https://mlsanity.com/paper/2503.08588/) (2025)
- [Mitigating Memorization In Language Models](https://mlsanity.com/paper/2410.02159/) (2024)
- [Mitigating Gender Bias in Code Large Language Models via Model Editing](https://mlsanity.com/paper/2410.07820/) (2024)
- [Keys to Robust Edits: from Theoretical Insights to Practical Advances](https://mlsanity.com/paper/2410.09338/) (2024)
- [Toxic Subword Pruning for Dialogue Response Generation on Large Language Models](https://mlsanity.com/paper/2410.04155/) (2024)
- [BiasGym: A Simple and Generalizable Framework for Analyzing and Removing Biases through Injection](https://mlsanity.com/paper/2508.08855/) (2025)

## Abstract (arXiv)

Large language models (LLMs) trained on vast corpora suffer from inevitable stereotype biases. Mitigating these biases with fine-tuning could be both costly and data-hungry. Model editing methods, which focus on modifying LLMs in a post-hoc manner, are of great potential to address debiasing. However, it lacks a comprehensive study that facilitates both internal and external model editing methods, supports various bias types, as well as understands the pros and cons of applying editing methods to stereotypical debiasing. To mitigate this gap, we carefully formulate social debiasing into an editing problem and benchmark seven existing model editing algorithms on stereotypical debiasing, i.e., debias editing. Our findings in three scenarios reveal both the potential and challenges of debias editing: (1) Existing model editing methods can effectively preserve knowledge and mitigate biases, while the generalization of debias effect from edited sentences to semantically equivalent sentences is limited.(2) Sequential editing highlights the robustness of SERAC (Mitchell et al. 2022b), while internal editing methods degenerate with the number of edits. (3) Model editing algorithms achieve generalization towards unseen biases both within the same type and from different types. In light of these findings, we further propose two simple but effective methods to improve debias editing, and experimentally show the effectiveness of the proposed methods.