# Toward Localizing and Repairing Bias in Transformer Attention Heads

arXiv: https://arxiv.org/abs/2607.12863 · HTML: https://mlsanity.com/paper/2607.12863/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 20 of its 29 references that are in the map.
- First posted on arXiv 14 Jul 2026.

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

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter](https://mlsanity.com/paper/1910.01108/) (2019)
- [Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings](https://mlsanity.com/paper/1607.06520/) (2016)
- [What Does BERT Look At? An Analysis of BERT's Attention](https://mlsanity.com/paper/1906.04341/) (2019)
- [StereoSet: Measuring stereotypical bias in pretrained language models](https://mlsanity.com/paper/2004.09456/) (2020)
- [Analyzing Multi-Head Self-Attention: Specialized Heads Do the Heavy Lifting, the Rest Can Be Pruned](https://mlsanity.com/paper/1905.09418/) (2019)
- [Are Sixteen Heads Really Better than One?](https://mlsanity.com/paper/1905.10650/) (2019)
- [Gender Bias in Coreference Resolution: Evaluation and Debiasing Methods](https://mlsanity.com/paper/1804.06876/) (2018)
- [Null It Out: Guarding Protected Attributes by Iterative Nullspace Projection](https://mlsanity.com/paper/2004.07667/) (2020)
- [Regularizing and Optimizing LSTM Language Models](https://mlsanity.com/paper/1708.02182/) (2017)
- [Towards Debiasing Sentence Representations](https://mlsanity.com/paper/2007.08100/) (2020)
- [Fairness Testing: Testing Software for Discrimination](https://mlsanity.com/paper/1709.03221/) (2017)
- [Bias in Machine Learning Software: Why? How? What to do?](https://mlsanity.com/paper/2105.12195/) (2021)
- [Automated Directed Fairness Testing](https://mlsanity.com/paper/1807.00468/) (2018)
- [Fairness Testing: A Comprehensive Survey and Analysis of Trends](https://mlsanity.com/paper/2207.10223/) (2022)
- [Concolic Testing for Deep Neural Networks](https://mlsanity.com/paper/1805.00089/) (2018)
- [Bias A-head? Analyzing Bias in Transformer-Based Language Model Attention Heads](https://mlsanity.com/paper/2311.10395/) (2023)
- [Attention Pruning: Automated Fairness Repair of Language Models via Surrogate Simulated Annealing](https://mlsanity.com/paper/2503.15815/) (2025)

## Abstract (arXiv)

Transformer language models are increasingly used as software components, yet biased outputs remain difficult to localize and repair inside the model. Existing fairness testing and repair methods largely operate at the input-output or retraining level, while recent work suggests that bias-related behavior can concentrate in a small set of attention heads. This paper studies whether attention heads can be localized and repaired through a targeted inference-time intervention. We introduce ROBIN, a white-box head-level fairness debugging method that ranks attention heads using sensitivity to fairness probes and removes a small bias subspace from selected head outputs. In a four-model pilot study, ROBIN reduces the measured WinoBias gap across all models while preserving language-modeling quality better than whole-head zeroing. These preliminary results suggest that head-level bias repair should consider not only which heads are selected, but also how selected heads are modified.