# An Empirical Survey of Model Merging Algorithms for Social Bias Mitigation

arXiv: https://arxiv.org/abs/2512.02689 · HTML: https://mlsanity.com/paper/2512.02689/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 20 of its 34 references that are in the map.
- First posted on arXiv 2 Dec 2025.

## Builds on (most cited first, 20 of 20)

- [GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding](https://mlsanity.com/paper/1804.07461/) (2018)
- [SuperGLUE: A Stickier Benchmark for General-Purpose Language Understanding Systems](https://mlsanity.com/paper/1905.00537/) (2019)
- [Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time](https://mlsanity.com/paper/2203.05482/) (2022)
- [Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings](https://mlsanity.com/paper/1607.06520/) (2016)
- [StereoSet: Measuring stereotypical bias in pretrained language models](https://mlsanity.com/paper/2004.09456/) (2020)
- [TIES-Merging: Resolving Interference When Merging Models](https://mlsanity.com/paper/2306.01708/) (2023)
- [BBQ: A Hand-Built Bias Benchmark for Question Answering](https://mlsanity.com/paper/2110.08193/) (2021)
- [Merging Models with Fisher-Weighted Averaging](https://mlsanity.com/paper/2111.09832/) (2021)
- [Null It Out: Guarding Protected Attributes by Iterative Nullspace Projection](https://mlsanity.com/paper/2004.07667/) (2020)
- [Gender Bias in Coreference Resolution](https://mlsanity.com/paper/1804.09301/) (2018)
- [BOLD: Dataset and Metrics for Measuring Biases in Open-Ended Language Generation](https://mlsanity.com/paper/2101.11718/) (2021)
- [Self-Diagnosis and Self-Debiasing: A Proposal for Reducing Corpus-Based Bias in NLP](https://mlsanity.com/paper/2103.00453/) (2021)
- [Model Merging in LLMs, MLLMs, and Beyond: Methods, Theories, Applications and Opportunities](https://mlsanity.com/paper/2408.07666/) (2024)
- [Counterfactual Data Augmentation for Mitigating Gender Stereotypes in Languages with Rich Morphology](https://mlsanity.com/paper/1906.04571/) (2019)
- [Towards Safer Large Language Models through Machine Unlearning](https://mlsanity.com/paper/2402.10058/) (2024)
- [DELLA-Merging: Reducing Interference in Model Merging through Magnitude-Based Sampling](https://mlsanity.com/paper/2406.11617/) (2024)
- [Ethos: Rectifying Language Models in Orthogonal Parameter Space](https://mlsanity.com/paper/2403.08994/) (2024)
- [Bias Vector: Mitigating Biases in Language Models with Task Arithmetic Approach](https://mlsanity.com/paper/2412.11679/) (2024)
- [Dynamic Fisher-weighted Model Merging via Bayesian Optimization](https://mlsanity.com/paper/2504.18992/) (2025)
- [Local Contrastive Editing of Gender Stereotypes](https://mlsanity.com/paper/2410.17739/) (2024)

## Abstract (arXiv)

Large language models (LLMs) are known to inherit and even amplify societal biases present in their pre-training corpora, threatening fairness and social trust. To address this issue, recent work has explored ``editing'' LLM parameters to mitigate social bias with model merging approaches; however, there is no empirical comparison. In this work, we empirically survey seven algorithms: Linear, Karcher Mean, SLERP, NuSLERP, TIES, DELLA, and Nearswap, applying 13 open weight models in the GPT, LLaMA, and Qwen families. We perform a comprehensive evaluation using three bias datasets (BBQ, BOLD, and HONEST) and measure the impact of these techniques on LLM performance in downstream tasks of the SuperGLUE benchmark. We find a trade-off between bias reduction and downstream performance: methods achieving greater bias mitigation degrade accuracy, particularly on tasks requiring reading comprehension and commonsense and causal reasoning. Among the merging algorithms, Linear, SLERP, and Nearswap consistently reduce bias while maintaining overall performance, with SLERP at moderate interpolation weights emerging as the most balanced choice. These results highlight the potential of model merging algorithms for bias mitigation, while indicating that excessive debiasing or inappropriate merging methods may lead to the degradation of important linguistic abilities.