# Fairness Mediator: Neutralize Stereotype Associations to Mitigate Bias in Large Language Models

arXiv: https://arxiv.org/abs/2504.07787 · HTML: https://mlsanity.com/paper/2504.07787/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Apr 2025.

## Built on by (most cited first, 8 of 8)

- [Pushing the Limits of Safety: A Technical Report on the ATLAS Challenge 2025](https://mlsanity.com/paper/2506.12430/) (2025)
- [Detoxifying Large Language Models via Autoregressive Reward Guided Representation Editing](https://mlsanity.com/paper/2510.01243/) (2025)
- [Semantic and Structural Analysis of Implicit Biases in Large Language Models: An Interpretable Approach](https://mlsanity.com/paper/2508.06155/) (2025)
- [SMA: Who Said That? Auditing Membership Leakage in Semi-Black-box RAG Controlling](https://mlsanity.com/paper/2508.09105/) (2025)
- [RoboView-Bias: Benchmarking Visual Bias in Embodied Agents for Robotic Manipulation](https://mlsanity.com/paper/2509.22356/) (2025)
- [Advertising in AI systems: Society must be vigilant](https://mlsanity.com/paper/2505.18425/) (2025)
- [When AI Writes, Whose Voice Remains? Quantifying Cultural Marker Erasure Across World English Varieties in Large Language Models](https://mlsanity.com/paper/2602.22145/) (2026)
- [MASCRDM: Multi-Agent System for Compliance Risk Detection and Mitigation in Training Process of Large Language Models](https://mlsanity.com/paper/2609.39107/) (2026)

## Abstract (arXiv)

LLMs have demonstrated remarkable performance across diverse applications, yet they inadvertently absorb spurious correlations from training data, leading to stereotype associations between biased concepts and specific social groups. These associations perpetuate and even amplify harmful social biases, raising significant fairness concerns. To mitigate such biases, prior studies have attempted to project model embeddings into unbiased spaces during inference. However, these approaches have shown limited effectiveness due to their weak alignment with downstream social biases. Inspired by the observation that concept cognition in LLMs is primarily represented through a linear associative memory mechanism, where key-value mapping occurs in the MLP layers, we posited that biased concepts and social groups are similarly encoded as entity (key) and information (value) pairs, which can be manipulated to promote fairer associations. To this end, we propose Fairness Mediator (FairMed), a bias mitigation framework that neutralizes stereotype associations. Our framework comprises two main components: a stereotype association prober and an adversarial debiasing neutralizer. The prober captures stereotype associations encoded within MLP layer activations by employing prompts centered around biased concepts to detect the emission probabilities for social groups. Subsequently, the adversarial debiasing neutralizer intervenes in MLP activations during inference to equalize the association probabilities among different social groups. Extensive experiments across nine protected attributes show that FairMed significantly outperforms SOTA methods in effectiveness. Compared to the most effective baseline, FairMed presents competitive efficiency by cutting mitigation overhead by hundreds of minutes. FairMed also maintains the LLM's language understanding capabilities without compromising overall performance.