# Debiasing Algorithm through Model Adaptation

arXiv: https://arxiv.org/abs/2310.18913 · HTML: https://mlsanity.com/paper/2310.18913/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 40 references that are in the map.
- First posted on arXiv 29 Oct 2023.

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

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge](https://mlsanity.com/paper/1803.05457/) (2018)
- [Pointer Sentinel Mixture Models](https://mlsanity.com/paper/1609.07843/) (2016)
- [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)
- [Transformer Feed-Forward Layers Are Key-Value Memories](https://mlsanity.com/paper/2012.14913/) (2020)
- [Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings](https://mlsanity.com/paper/1607.06520/) (2016)
- [Mass-Editing Memory in a Transformer](https://mlsanity.com/paper/2210.07229/) (2022)
- [Language (Technology) is Power: A Critical Survey of "Bias" in NLP](https://mlsanity.com/paper/2005.14050/) (2020)
- [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)
- [Gender Bias in Coreference Resolution: Evaluation and Debiasing Methods](https://mlsanity.com/paper/1804.06876/) (2018)
- [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)
- [Gender Bias in Coreference Resolution](https://mlsanity.com/paper/1804.09301/) (2018)
- [Direct and Indirect Effects](https://mlsanity.com/paper/1301.2300/) (2013)
- [LEACE: Perfect linear concept erasure in closed form](https://mlsanity.com/paper/2306.03819/) (2023)
- [Evaluating Gender Bias in Machine Translation](https://mlsanity.com/paper/1906.00591/) (2019)
- [Gender Bias in Neural Natural Language Processing](https://mlsanity.com/paper/1807.11714/) (2018)
- [Counterfactual Data Augmentation for Mitigating Gender Stereotypes in Languages with Rich Morphology](https://mlsanity.com/paper/1906.04571/) (2019)
- [Causal Mediation Analysis for Interpreting Neural NLP: The Case of Gender Bias](https://mlsanity.com/paper/2004.12265/) (2020)
- [Gender Bias in Machine Translation](https://mlsanity.com/paper/2104.06001/) (2021)
- [Linear Adversarial Concept Erasure](https://mlsanity.com/paper/2201.12091/) (2022)
- [Sustainable Modular Debiasing of Language Models](https://mlsanity.com/paper/2109.03646/) (2021)
- [A Survey on Gender Bias in Natural Language Processing](https://mlsanity.com/paper/2112.14168/) (2021)
- [A Trip Towards Fairness: Bias and De-Biasing in Large Language Models](https://mlsanity.com/paper/2305.13862/) (2023)
- [AdapterBias: Parameter-efficient Token-dependent Representation Shift for Adapters in NLP Tasks](https://mlsanity.com/paper/2205.00305/) (2022)
- [Don't Forget About Pronouns: Removing Gender Bias in Language Models Without Losing Factual Gender Information](https://mlsanity.com/paper/2206.10744/) (2022)

## Built on by (most cited first, 24 of 24)

- [Safeguarding Large Language Models: A Survey](https://mlsanity.com/paper/2406.02622/) (2024)
- [Building Guardrails for Large Language Models](https://mlsanity.com/paper/2402.01822/) (2024)
- [Navigating the Risks: A Survey of Security, Privacy, and Ethics Threats in LLM-Based Agents](https://mlsanity.com/paper/2411.09523/) (2024)
- [Fairness in Large Language Models: A Taxonomic Survey](https://mlsanity.com/paper/2404.01349/) (2024)
- [Attribution Analysis Meets Model Editing: Advancing Knowledge Correction in Vision Language Models with VisEdit](https://mlsanity.com/paper/2408.09916/) (2024)
- [Lifelong Knowledge Editing for Vision Language Models with Low-Rank Mixture-of-Experts](https://mlsanity.com/paper/2411.15432/) (2024)
- [Look Within, Why LLMs Hallucinate: A Causal Perspective](https://mlsanity.com/paper/2407.10153/) (2024)
- [Potential and Challenges of Model Editing for Social Debiasing](https://mlsanity.com/paper/2402.13462/) (2024)
- [Mitigating Biases of Large Language Models in Stance Detection with Counterfactual Augmented Calibration](https://mlsanity.com/paper/2402.14296/) (2024)
- [Is Free Self-Alignment Possible?](https://mlsanity.com/paper/2406.03642/) (2024)
- [Preserving Task-Relevant Information Under Linear Concept Removal](https://mlsanity.com/paper/2506.10703/) (2025)
- [Mitigating Gender Bias in Code Large Language Models via Model Editing](https://mlsanity.com/paper/2410.07820/) (2024)
- [KLAAD: Refining Attention Mechanisms to Reduce Societal Bias in Generative Language Models](https://mlsanity.com/paper/2507.19962/) (2025)
- [Runtime Monitoring and Enforcement of Conditional Fairness in Generative AIs](https://mlsanity.com/paper/2404.16663/) (2024)
- [Investigating Hallucination in Conversations for Low Resource Languages](https://mlsanity.com/paper/2507.22720/) (2025)
- [BiasFreeBench: a Benchmark for Mitigating Bias in Large Language Model Responses](https://mlsanity.com/paper/2510.00232/) (2025)
- [Attention, May I Have Your Decision? Localizing Generative Choices in Diffusion Models](https://mlsanity.com/paper/2604.06052/) (2026)
- [Neuron-Level Interventions for Gendered and Gender-Neutral Generation in Language Models](https://mlsanity.com/paper/2605.30717/) (2026)
- [Gender Bias of LLM in Economics: An Existentialism Perspective](https://mlsanity.com/paper/2410.19775/) (2024)
- [Advertising in AI systems: Society must be vigilant](https://mlsanity.com/paper/2505.18425/) (2025)
- [DeFrame: Debiasing Large Language Models Against Framing Effects](https://mlsanity.com/paper/2602.04306/) (2026)
- [A Critical Review of Predominant Bias in Neural Networks](https://mlsanity.com/paper/2502.11031/) (2025)
- [Debiasing Large Language Models in Thai Political Stance Detection via Counterfactual Calibration](https://mlsanity.com/paper/2509.21946/) (2025)
- [GKnow: Measuring the Entanglement of Gender Bias and Factual Gender](https://mlsanity.com/paper/2605.12299/) (2026)

## Abstract (arXiv)

Large language models are becoming the go-to solution for the ever-growing number of tasks. However, with growing capacity, models are prone to rely on spurious correlations stemming from biases and stereotypes present in the training data. This work proposes a novel method for detecting and mitigating gender bias in language models. We perform causal analysis to identify problematic model components and discover that mid-upper feed-forward layers are most prone to convey bias. Based on the analysis results, we intervene in the model by applying a linear projection to the weight matrices of these layers. Our titular method, DAMA, significantly decreases bias as measured by diverse metrics while maintaining the model's performance on downstream tasks. We release code for our method and models, which retrain LLaMA's state-of-the-art performance while being significantly less biased.